Triple

T20688015
Position Surface form Disambiguated ID Type / Status
Subject Luke Doolan E508471 entity
Predicate edited P1932 FINISHED
Object "Hesher" 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: "Hesher" | Statement: [Luke Doolan, edited, "Hesher"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: "Hesher"
Context triple: [Luke Doolan, edited, "Hesher"]
  • A. Hesher chosen
    Hesher is a 2010 dark comedy-drama film about a disruptive, anarchic drifter who upends the lives of a grieving family.
  • B. The Harvest
    The Harvest is a landscape painting by French Barbizon school artist Charles-François Daubigny, depicting rural agricultural life with his characteristic naturalistic light and atmosphere.
  • C. The Harvest
    The Harvest is a 1992 American thriller film directed by David Marconi, known for its dark, suspenseful plot involving organ trafficking.
  • D. The Harvest
    The Harvest is an Impressionist painting by Camille Pissarro depicting rural agricultural laborers working in the fields.
  • E. The Feast
    "The Feast" is a notable painting by Georgian modernist artist Lado Gudiashvili, reflecting his distinctive, fantastical style and exploration of national themes.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6beaddfe88190897b8963fa8b2245 completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 11:45 a.m.