Triple

T15738009
Position Surface form Disambiguated ID Type / Status
Subject CAF A36 tram E381525 entity
Predicate manufacturer P490 FINISHED
Object CAF E59649 NE FINISHED

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: CAF | Statement: [CAF A36 tram, manufacturer, CAF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CAF
Context triple: [CAF A36 tram, manufacturer, CAF]
  • A. CAF
    CAF is the commonly used acronym for the Canadian Armed Forces, the unified military organization responsible for defending Canada and supporting international peace and security operations.
  • B. CAF chosen
    CAF is a Spanish multinational company that designs and manufactures railway vehicles and related transport equipment used by metro systems worldwide.
  • C. CAF
    CAF is the commonly used abbreviation for the Chief of Air Force, the professional head of an air force service.
  • D. CAF
    CAF is the acronym for "Comando de Apoyo a la Fuerza," a military support command unit within the Spanish Armed Forces.
  • E. CAF
    CAF is an abbreviation for the Federation of Rhodesia and Nyasaland, a former semi-independent colonial federation in south-central Africa that existed from 1953 to 1963 under British rule.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd6eb888190b7a9b07b76e62c0d completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff830336248190a8bbd8153dd95daa completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.