Triple

T16100124
Position Surface form Disambiguated ID Type / Status
Subject Liam Flockhart E390593 entity
Predicate familyName P18 FINISHED
Object Flockhart E1130879 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: Flockhart | Statement: [Liam Flockhart, familyName, Flockhart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flockhart
Context triple: [Liam Flockhart, familyName, Flockhart]
  • A. Flockhart chosen
    Flockhart is a Scottish-origin surname most prominently associated with American actress Calista Flockhart.
  • B. McTeague
    McTeague is a naturalist novel by Frank Norris that follows the brutal moral and psychological decline of a San Francisco dentist consumed by greed and violence.
  • C. Morrel
    Morrel is a French surname most notably associated with characters in Alexandre Dumas’ novel "The Count of Monte Cristo."
  • D. The Quigley
    The Quigley is a notorious water obstacle course at the U.S. Marine Corps Officer Candidates School, known for its muddy trenches, submerged passages, and physically demanding conditions.
  • E. De Gemeene Gratie
    De Gemeene Gratie is a major theological work by Abraham Kuyper that develops his doctrine of “common grace,” explaining how God’s grace operates in all of culture and society, not only within the church.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1ff6756948190a7f5ecb375e59701 completed April 17, 2026, 9:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb9d6140819087f9b3dc549c4aec completed May 10, 2026, 2:21 a.m.
Created at: April 10, 2026, 5 a.m.