Triple

T19288072
Position Surface form Disambiguated ID Type / Status
Subject STT E482365 entity
Predicate hasBloombergTicker P1447 FINISHED
Object STT US 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: STT US | Statement: [STT, hasBloombergTicker, STT US]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: STT US
Context triple: [STT, hasBloombergTicker, STT US]
  • A. STT
    STT is the IATA airport code for Cyril E. King Airport, the main international gateway to St. Thomas in the U.S. Virgin Islands.
  • B. STT chosen
    STT is the stock ticker symbol for State Street Corporation, a major U.S.-based financial services and asset management company.
  • C. STT
    STT is the acronym for the Société des Transports de Tunis, the public transportation company serving the Tunis metropolitan area in Tunisia.
  • D. USAT
    USAT is the commonly used abbreviation for USA Triathlon, the national governing body for triathlon and related multisport disciplines in the United States.
  • E. T US
    T US is the Bloomberg ticker symbol for AT&T Inc., a major American telecommunications and media company.
  • 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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc043fa481909bbe281a70fb508e completed April 20, 2026, 10:12 a.m.
Created at: April 10, 2026, 1:30 p.m.