Triple

T7528238
Position Surface form Disambiguated ID Type / Status
Subject Papeete E177950 entity
Predicate timeZone P109 FINISHED
Object Tahiti Time E208145 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: Tahiti Time | Statement: [Papeete, timeZone, Tahiti Time]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tahiti Time
Context triple: [Papeete, timeZone, Tahiti Time]
  • A. Tahiti Time chosen
    Tahiti Time is the standard time zone used in Tahiti and surrounding islands in French Polynesia, corresponding to UTC−10:00 without daylight saving time.
  • B. Reo Tahiti
    Reo Tahiti is the indigenous Polynesian language spoken primarily in Tahiti and other islands of French Polynesia.
  • C. Niue Time
    Niue Time is the standard time observed in the island nation of Niue, a small self-governing state in free association with New Zealand in the South Pacific Ocean.
  • D. Palau Time
    Palau Time is the standard time zone used in the Republic of Palau, corresponding to UTC+9 hours.
  • E. Havaiki
    Havaiki is a variant spelling of Hawaiki, the legendary ancestral homeland in Polynesian mythology from which many Pacific peoples trace their origins.
  • 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_69c69f29bf3081909a146aec7755f185 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f81e19208190965f211d057f7fdf completed March 27, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84639c19881909e1736afc01a020d completed March 28, 2026, 9:20 p.m.
Created at: March 27, 2026, 3:47 p.m.