Triple

T21857672
Position Surface form Disambiguated ID Type / Status
Subject Town of Southampton E539671 entity
Predicate containsSettlement P847 FINISHED
Object Speonk 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: Speonk | Statement: [Town of Southampton, containsSettlement, Speonk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Speonk
Context triple: [Town of Southampton, containsSettlement, Speonk]
  • A. Speonk chosen
    Speonk is a hamlet in the Town of Southampton on Long Island, New York, known for its Long Island Rail Road station on the Montauk Branch.
  • B. Speonk, New York
    Speonk, New York is a small hamlet on the South Shore of Long Island known for its rural character and proximity to the beaches and waterways of eastern Suffolk County.
  • C. Zonnemaire
    Zonnemaire is a small village in the Dutch province of Zeeland, notable as the birthplace of Nobel Prize–winning physicist Pieter Zeeman.
  • D. Westhoek
    Westhoek is a historic region in western Belgium and northern France known for its World War I battlefields, rural landscapes, and Flemish cultural heritage.
  • E. Bredevoort
    Bredevoort is a small historic town in the Dutch province of Gelderland, known for its well-preserved medieval character and its reputation as a national "book town."
  • 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_69e0c47829648190bbe2d1d7033768ec completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0d638721c8190918fc6ad9c5d5bf6 completed April 28, 2026, 3:46 p.m.
Created at: April 16, 2026, 6:56 p.m.