Triple

T17082029
Position Surface form Disambiguated ID Type / Status
Subject Rongo E414495 entity
Predicate worshippedIn P2291 FINISHED
Object Mangaia E230620 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: Mangaia | Statement: [Rongo, worshippedIn, Mangaia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangaia
Context triple: [Rongo, worshippedIn, Mangaia]
  • A. Mangaia chosen
    Mangaia is the southernmost and second-largest of the Cook Islands, known for its rugged limestone cliffs, ancient makatea landscape, and rich Polynesian culture.
  • B. Kaiarahi
    Kaiarahi is a roll-on/roll-off passenger and vehicle ferry operated by New Zealand’s Interislander service across Cook Strait.
  • C. Rakiraki
    Rakiraki is a small coastal town in northern Viti Levu, Fiji, known as a local commercial center and gateway to nearby islands and dive sites.
  • D. Arutua
    Arutua is a coral atoll in French Polynesia’s Tuamotu Archipelago, known for its lagoon, pearl farming, and traditional Polynesian community.
  • E. Korangi
    Korangi is a major industrial and residential area in Karachi, Pakistan, known for its large industrial estate and dense urban population.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbe408d48190b4f52c2102eae7c2 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ee416c4819087e7ae0ead47867a completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:34 a.m.