Triple

T18823361
Position Surface form Disambiguated ID Type / Status
Subject Robert California E460320 entity
Predicate employerInSeries P40735 FINISHED
Object Sabre 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: Sabre | Statement: [Robert California, employerInSeries, Sabre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sabre
Context triple: [Robert California, employerInSeries, Sabre]
  • A. Sabre chosen
    Sabre is a leading global travel technology company that provides software and distribution solutions for airlines, hotels, and travel agencies.
  • B. Sabre Holdings
    Sabre Holdings is a major travel technology and global distribution systems company that provides software and services to airlines, hotels, and travel agencies worldwide.
  • C. Mariot
    Mariot is a given name most notably borne by the 18th-century British Royal Navy officer Mariot Arbuthnot.
  • D. CAC Sabre
    The CAC Sabre was an Australian-built, Rolls-Royce Avon–powered development of the F-86 Sabre fighter jet, adapted and produced by the Commonwealth Aircraft Corporation for service with the Royal Australian Air Force.
  • E. Ebasco
    Ebasco was a major American engineering and construction firm known for designing and building large-scale power plants, including nuclear facilities worldwide.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6bce5588190bd0aefcd0c51edad completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.