Triple

T8939097
Position Surface form Disambiguated ID Type / Status
Subject Wilmington International Airport E212851 entity
Predicate FAAcode P420 FINISHED
Object ILM E767351 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: ILM | Statement: [Wilmington International Airport, FAAcode, ILM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ILM
Context triple: [Wilmington International Airport, FAAcode, ILM]
  • A. ILM
    ILM (Industrial Light & Magic) is a pioneering visual effects and virtual production company renowned for its groundbreaking work in film and television.
  • B. ILM chosen
    ILM is the IATA airport code for Wilmington International Airport, a commercial airport serving Wilmington, North Carolina.
  • C. Skillset Film Skills Fund
    Skillset Film Skills Fund is a UK-based initiative focused on developing and supporting professional skills and training within the British film industry.
  • D. ILC
    The International Law Commission (ILC) is a United Nations body of legal experts tasked with developing and codifying international law.
  • E. ILC
    ILC is the commonly used abbreviation for the International Labour Conference, the annual policy-making body of the International Labour Organization that sets international labor standards.
  • 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_69ca839694c88190b324ffeb43d23b08 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66b7484481909e0d7610552f5386 completed April 1, 2026, 12:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc937ded08190a67fd4457b6458ff completed April 3, 2026, 2:05 p.m.
Created at: March 30, 2026, 6:58 p.m.