Triple

T22320973
Position Surface form Disambiguated ID Type / Status
Subject Luna 14 E551782 entity
Predicate followedBy P78 FINISHED
Object Luna 15 NE NERFINISHED

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: Luna 15 | Statement: [Luna 14, followedBy, Luna 15]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luna 15
Context triple: [Luna 14, followedBy, Luna 15]
  • A. Luna 15 chosen
    Luna 15 was a Soviet unmanned lunar probe launched in 1969 that attempted to return samples from the Moon but crashed during its descent.
  • B. Luna 13
    Luna 13 was a Soviet robotic spacecraft that successfully soft-landed on the Moon in 1966 and transmitted panoramic images and data about the lunar surface.
  • C. Luna 21
    Luna 21 was a Soviet lunar mission that delivered the Lunokhod 2 rover to the Moon in 1973 as part of the USSR's robotic exploration program.
  • D. Luna 14
    Luna 14 was a Soviet robotic spacecraft launched in 1968 to study the Moon’s gravitational field and test tracking and communication systems for future lunar missions.
  • E. Luna 20
    Luna 20 was a Soviet robotic lunar sample-return mission that successfully collected and returned soil from the Moon’s surface in 1972.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15764d3a48190af79ce4642b7f563 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.