Triple

T18398419
Position Surface form Disambiguated ID Type / Status
Subject Qingdao Jiaodong International Airport E449927 entity
Predicate IATAcode P418 FINISHED
Object TAO 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: TAO | Statement: [Qingdao Jiaodong International Airport, IATAcode, TAO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TAO
Context triple: [Qingdao Jiaodong International Airport, IATAcode, TAO]
  • A. TAO chosen
    TAO is the UN/LOCODE designation for the major Chinese seaport of Qingdao, a key hub for international maritime trade.
  • B. TAO
    TAO is the ICAO airline designator assigned to Aeromar, a regional airline based in Mexico.
  • C. TAU
    TAU is a major public research university located in Tel Aviv, Israel, known for its strong programs across science, engineering, humanities, and the arts.
  • D. TAU
    TAU is the station code for Tacuba, an interchange station on Mexico City’s Metro system.
  • E. Tao I
    Tao I was an ancient Egyptian pharaoh associated with the late Second Intermediate Period, known primarily as an early ruler in the Theban line that opposed Hyksos control.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5184879548190b7f428e2d4c2caa4 completed April 19, 2026, 6 p.m.
Created at: April 10, 2026, 10:46 a.m.