Triple

T16955249
Position Surface form Disambiguated ID Type / Status
Subject City of Shellharbour E411282 entity
Predicate contains P35 FINISHED
Object Dunmore E1236752 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: Dunmore | Statement: [City of Shellharbour, contains, Dunmore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dunmore
Context triple: [City of Shellharbour, contains, Dunmore]
  • A. Dunmore
    Dunmore is a borough in northeastern Pennsylvania that functions as a residential and industrial community adjacent to the city of Scranton.
  • B. Dunmore chosen
    Dunmore is a locality in the Shellharbour region of New South Wales, Australia, known historically for its railway station on the South Coast line.
  • C. Dinwiddie
    Dinwiddie is an unincorporated community in south-central Virginia that serves as the administrative center of Dinwiddie County.
  • D. Dunmore Town
    Dunmore Town is a small, historic Bahamian town on Harbour Island known for its colonial architecture and pink sand beaches.
  • E. Pettycur
    Pettycur is a small coastal settlement and harbour area near Kinghorn in Fife, Scotland, known for its beach and views across the Firth of Forth.
  • 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_69d886c9c9d481909afe222093641cae completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d01bb700819082a441c124be3cb6 completed April 18, 2026, 6:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d464762c8190a734ffdd83633f70 completed May 10, 2026, 6:54 p.m.
Created at: April 10, 2026, 5:31 a.m.