Triple

T17161082
Position Surface form Disambiguated ID Type / Status
Subject TRG E416478 entity
Predicate hasICAOCode P419 FINISHED
Object NZTG E416479 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: NZTG | Statement: [TRG, hasICAOCode, NZTG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NZTG
Context triple: [TRG, hasICAOCode, NZTG]
  • A. NZTG chosen
    NZTG is the ICAO airport code for Tauranga Airport in Tauranga, New Zealand.
  • B. ZNG
    ZNG is the three-letter station code used to identify Notting Hill Gate Underground station on the London Underground network.
  • C. NTZ
    NTZ is the commonly used abbreviation for the Lamlash Bay no-take marine conservation zone off the Isle of Arran in Scotland.
  • D. NZQN
    NZQN is the ICAO airport code for Queenstown Airport, a major tourist gateway located in Queenstown on New Zealand’s South Island.
  • E. NZGS
    NZGS is the ICAO airport code for Gisborne Airport in New Zealand, a regional airport known for its unique railway line crossing the main runway.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f911114481909c865b2e2d3b3a2b completed April 18, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0148376bc081908372366203a27fa8 completed May 11, 2026, 3:08 a.m.
Created at: April 10, 2026, 5:37 a.m.