Triple

T4993971
Position Surface form Disambiguated ID Type / Status
Subject Viking 2 E112199 entity
Predicate hasComponent P35 FINISHED
Object Viking 2 orbiter E485882 NE FINISHED

How this triple was built (2 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: Viking 2 orbiter | Statement: [Viking 2, hasComponent, Viking 2 orbiter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viking 2 orbiter
Context triple: [Viking 2, hasComponent, Viking 2 orbiter]
  • A. Viking 2
    Viking 2 was a NASA spacecraft and lander that conducted scientific investigations on the surface of Mars as part of the Viking program in the 1970s.
  • B. Viking Orbiter chosen
    Viking Orbiter was a pair of NASA spacecraft launched in the 1970s that orbited Mars to map its surface, study its atmosphere, and support the Viking landers.
  • C. Viking 1
    Viking 1 was a NASA spacecraft that became the first successful lander on Mars, conducting detailed imaging and scientific experiments on the Martian surface starting in 1976.
  • D. Mariner 9
    Mariner 9 was a NASA robotic spacecraft that became the first artificial satellite of Mars, revolutionizing our understanding of the planet’s surface and atmosphere in the early 1970s.
  • E. Venera 9
    Venera 9 was a Soviet spacecraft that became the first human-made probe to successfully return images from the surface of Venus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4432b32c81909f3b3c6bd10f0653 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd729d3d448190a414a003a75104f6 completed March 20, 2026, 4:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed90afc5c8190b205341d1e9dc7bc completed March 21, 2026, 5:44 p.m.
Created at: March 20, 2026, 1:34 p.m.