Triple

T19420944
Position Surface form Disambiguated ID Type / Status
Subject International Terminal B E485850 entity
Predicate shortName P43 FINISHED
Object TBIT 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: TBIT | Statement: [International Terminal B, shortName, TBIT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TBIT
Context triple: [International Terminal B, shortName, TBIT]
  • A. TBIT chosen
    TBIT is the commonly used abbreviation for the Tom Bradley International Terminal at Los Angeles International Airport, a major hub for international air travel.
  • B. TIB
    TIB is a major German academic institution and library specializing in science and technology information, including digital and research data services.
  • C. BIT
    BIT is the stock exchange code commonly used to identify securities listed on Borsa Italiana, the main Italian stock exchange based in Milan.
  • D. BIT
    BIT is the vehicle registration code for the district of Bitburg-Prüm in the German state of Rhineland-Palatinate.
  • E. BIT
    BIT is the abbreviated name of Switzerland’s Federal Office of Information Technology, Systems and Telecommunication, the central federal provider of IT and communication services.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63214d768819082129100d7116521 completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.