Triple

T747478
Position Surface form Disambiguated ID Type / Status
Subject Perseverance rover E15374 entity
Predicate usesTechnology P1485 FINISHED
Object Terrain-Relative Navigation
Terrain-Relative Navigation is a guidance technology that enables spacecraft to autonomously analyze surface features in real time and adjust their descent path for a precise and safe landing.
E88916 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Terrain-Relative Navigation | Statement: [Perseverance rover, usesTechnology, Terrain-Relative Navigation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terrain-Relative Navigation
Context triple: [Perseverance rover, usesTechnology, Terrain-Relative Navigation]
  • A. Mars Science Laboratory entry, descent, and landing modeling
    Mars Science Laboratory entry, descent, and landing modeling is the suite of analytical and computational tools used to predict and optimize the Curiosity rover’s atmospheric entry, parachute descent, and landing performance on Mars.
  • B. Fine Guidance Sensor
    The Fine Guidance Sensor is a high-precision pointing and stabilization instrument on the James Webb Space Telescope that locks onto guide stars to keep the observatory accurately aimed during observations.
  • C. Attitude and Articulation Control Subsystem computer
    The Attitude and Articulation Control Subsystem computer is the dedicated onboard system on Voyager 2 responsible for controlling the spacecraft’s orientation and the pointing of its instruments and antennas.
  • D. Starship Human Landing System
    The Starship Human Landing System is NASA’s selected lunar lander variant of SpaceX’s Starship spacecraft, designed to transport astronauts between lunar orbit and the Moon’s surface for Artemis missions.
  • E. Nomad space probe
    The Nomad space probe is a fictional, highly advanced robotic spacecraft from the Star Trek universe that becomes a powerful and dangerous hybrid entity after merging with an alien probe.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Terrain-Relative Navigation
Triple: [Perseverance rover, usesTechnology, Terrain-Relative Navigation]
Generated description
Terrain-Relative Navigation is a guidance technology that enables spacecraft to autonomously analyze surface features in real time and adjust their descent path for a precise and safe landing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terrain-Relative Navigation
Target entity description: Terrain-Relative Navigation is a guidance technology that enables spacecraft to autonomously analyze surface features in real time and adjust their descent path for a precise and safe landing.
  • A. Mars Science Laboratory entry, descent, and landing modeling
    Mars Science Laboratory entry, descent, and landing modeling is the suite of analytical and computational tools used to predict and optimize the Curiosity rover’s atmospheric entry, parachute descent, and landing performance on Mars.
  • B. Fine Guidance Sensor
    The Fine Guidance Sensor is a high-precision pointing and stabilization instrument on the James Webb Space Telescope that locks onto guide stars to keep the observatory accurately aimed during observations.
  • C. Attitude and Articulation Control Subsystem computer
    The Attitude and Articulation Control Subsystem computer is the dedicated onboard system on Voyager 2 responsible for controlling the spacecraft’s orientation and the pointing of its instruments and antennas.
  • D. Starship Human Landing System
    The Starship Human Landing System is NASA’s selected lunar lander variant of SpaceX’s Starship spacecraft, designed to transport astronauts between lunar orbit and the Moon’s surface for Artemis missions.
  • E. Nomad space probe
    The Nomad space probe is a fictional, highly advanced robotic spacecraft from the Star Trek universe that becomes a powerful and dangerous hybrid entity after merging with an alien probe.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a49358aa308190adbc9b5a0a2adcf9 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a62dd1bc819094a3814654448ae3 completed March 1, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69a654e664e4819081badaf0ba0d86e5 completed March 3, 2026, 3:26 a.m.
NEDg Description generation batch_69a655e0a2608190801fb67856bc2ac4 completed March 3, 2026, 3:30 a.m.
NED2 Entity disambiguation (via description) batch_69a65704a964819097ad5074e83303b4 completed March 3, 2026, 3:35 a.m.
Created at: March 1, 2026, 7:37 p.m.