Triple

T21870590
Position Surface form Disambiguated ID Type / Status
Subject Central Taiwan E539989 entity
Predicate contains P35 FINISHED
Object Puli Township 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: Puli Township | Statement: [Central Taiwan, contains, Puli Township]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puli Township
Context triple: [Central Taiwan, contains, Puli Township]
  • A. Puli Township chosen
    Puli Township is a mountainous town in central Taiwan known as the geographic center of the island and a gateway to Sun Moon Lake.
  • B. Tehkummah Township
    Tehkummah Township is a small rural municipality located on Manitoulin Island in northeastern Ontario, Canada.
  • C. Mahlaing Township
    Mahlaing Township is an administrative township located within Myanmar's central Mandalay Region.
  • D. Paipoonge Township
    Paipoonge Township is a rural community in northwestern Ontario, Canada, that forms part of the Municipality of Oliver Paipoonge.
  • E. Kanaranzi Township
    Kanaranzi Township is a small rural civil township located in Nobles County in southwestern Minnesota, United States.
  • 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_69e0c478f59081909d54302b57fc1ce3 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0f33509d08190b33775abb84d5255 completed April 28, 2026, 5:49 p.m.
Created at: April 16, 2026, 6:57 p.m.