Triple

T16555909
Position Surface form Disambiguated ID Type / Status
Subject Paul Heaton E402200 entity
Predicate familyName P18 FINISHED
Object Heaton E353449 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: Heaton | Statement: [Paul Heaton, familyName, Heaton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heaton
Context triple: [Paul Heaton, familyName, Heaton]
  • A. Heaton
    Heaton is a suburban residential area within the town of Bolton in Greater Manchester, England.
  • B. Heaton chosen
    Heaton is a surname most notably associated with American actress Patricia Heaton, known for her roles in popular television sitcoms.
  • C. Heaton Park
    Heaton Park is a large historic public park in Manchester, England, known for its expansive green spaces, woodland, boating lake, and the Grade I listed Heaton Hall.
  • D. Heaton Moor
    Heaton Moor is a suburban residential area in Greater Manchester, England, known for its leafy streets, Victorian and Edwardian architecture, and village-like center with independent shops and cafes.
  • E. Heaton Flats
    Heaton Flats is a popular trailhead and camping area in the San Gabriel Mountains of Southern California, serving as a gateway to several rugged backcountry hikes.
  • 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_69d8838648088190acf97ef11fc3f61b completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34fc99f648190b40869ce52d351c8 completed April 18, 2026, 9:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067ba4bec81909dfa87bcd2bfa7be completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 5:15 a.m.