Triple

T22766437
Position Surface form Disambiguated ID Type / Status
Subject Luna 21 E563138 entity
Predicate predecessor P97 FINISHED
Object Luna 20 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 20 | Statement: [Luna 21, predecessor, Luna 20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luna 20
Context triple: [Luna 21, predecessor, Luna 20]
  • A. Luna 20 chosen
    Luna 20 was a Soviet robotic lunar sample-return mission that successfully collected and returned soil from the Moon’s surface in 1972.
  • B. Luna 23
    Luna 23 was a Soviet robotic lunar lander mission from the Luna program in the 1970s, intended to return soil samples from the Moon but ultimately failing to complete its sample-return objective.
  • C. Luna 22
    Luna 22 was a Soviet lunar orbiter mission in the 1970s that conducted detailed mapping and scientific study of the Moon’s surface and environment.
  • D. Luna 28
    Luna 28 is a planned Russian lunar mission intended to return samples from the Moon’s surface to Earth as part of the Luna exploration program.
  • E. Luna 15
    Luna 15 was a Soviet unmanned lunar probe launched in 1969 that attempted to return samples from the Moon but crashed during its descent.
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a80e2688190b76844c408929d32 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:26 p.m.