Triple

T17351885
Position Surface form Disambiguated ID Type / Status
Subject Katherine Airport E421832 entity
Predicate hasICAOcode P419 FINISHED
Object YPTN E1261993 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: YPTN | Statement: [Katherine Airport, hasICAOcode, YPTN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YPTN
Context triple: [Katherine Airport, hasICAOcode, YPTN]
  • A. YPTN chosen
    YPTN is the ICAO airport code for RAAF Base Tindal, a Royal Australian Air Force base and military airfield in the Northern Territory of Australia.
  • B. YPT
    YPT is the IATA airport code for Pelee Island Airport, a small regional airport serving Pelee Island in Ontario, Canada.
  • C. JNPT
    JNPT (Jawaharlal Nehru Port Trust) is India’s largest container port, located near Mumbai on the Arabian Sea coast in Maharashtra.
  • D. YRT
    YRT is the public transit system serving Ontario’s York Region, operating local and rapid buses that connect communities north of Toronto.
  • E. PTK
    PTK is the Indian Railways station code for Pathankot Junction, a major railway hub in the northern Indian state of Punjab.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a2dae648190b7f3487919a446af completed April 19, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0195585e5881909b0ad386b65112ba completed May 11, 2026, 8:37 a.m.
Created at: April 10, 2026, 5:44 a.m.