Triple

T17741633
Position Surface form Disambiguated ID Type / Status
Subject SPERT-IV E442872 entity
Predicate partOf P40 FINISHED
Object SPERT program 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: SPERT program | Statement: [SPERT-IV, partOf, SPERT program]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SPERT program
Context triple: [SPERT-IV, partOf, SPERT program]
  • A. SPERT-I
    SPERT-I was the first reactor in the Special Power Excursion Reactor Test series, designed to study reactor safety and behavior under rapid power excursion conditions.
  • B. SPERT-II
    SPERT-II was a research nuclear reactor used in the SPERT program to study reactor safety and power excursion behavior under experimental conditions.
  • C. SPERT-IV chosen
    SPERT-IV was a research reactor facility used in the SPERT program to study reactor safety and transient behavior under power excursion conditions.
  • D. SPERT-III
    SPERT-III was a U.S. experimental nuclear research reactor used in the mid-20th century to study reactor safety and power excursion behavior.
  • E. ERTS program
    The ERTS program (Earth Resources Technology Satellite) was NASA’s early satellite initiative that evolved into the Landsat program, pioneering the use of space-based imagery for monitoring Earth’s land resources.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47acd780c8190b1308ef0aca00f5c completed April 19, 2026, 6:48 a.m.
Created at: April 10, 2026, 10:09 a.m.