Triple

T21101295
Position Surface form Disambiguated ID Type / Status
Subject C3.ai E519909 entity
Predicate formerName P65 FINISHED
Object C3 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: C3 | Statement: [C3.ai, formerName, C3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: C3
Context triple: [C3.ai, formerName, C3]
  • A. C3 chosen
    C3 is the route designation for the Tokyo Gaikan Expressway, a major orbital expressway forming part of the ring road system around Tokyo, Japan.
  • B. C30
    C30 is a class of metro rolling stock used on the Stockholm metro (SL) system.
  • C. 3C
    3C is a well-known astronomical catalog of extragalactic radio sources, including many prominent quasars and radio galaxies.
  • D. C3F
    C3F is the official abbreviation for the United States Navy's Third Fleet, a major operational fleet responsible for naval forces in the eastern and northern Pacific Ocean.
  • E. C2
    C2 is the software consultancy founded by Ward Cunningham, best known for creating the first wiki and contributing to agile software development practices.
  • 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_69e0b508d8dc81909be940dafe36c8f7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e71b5e16cc81908257ccf8c9a59117 completed April 21, 2026, 6:38 a.m.
Created at: April 16, 2026, 2:53 p.m.