Triple

T15871817
Position Surface form Disambiguated ID Type / Status
Subject Hour of Power E384846 entity
Predicate presenter P83 FINISHED
Object Sheila Schuller Coleman E1186483 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: Sheila Schuller Coleman | Statement: [Hour of Power, presenter, Sheila Schuller Coleman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sheila Schuller Coleman
Context triple: [Hour of Power, presenter, Sheila Schuller Coleman]
  • A. Sheila Schuller Coleman chosen
    Sheila Schuller Coleman is an American pastor and author best known for her leadership role at the Crystal Cathedral and as the daughter of televangelist Robert H. Schuller.
  • B. Anita Coleman
    Anita Coleman is a fictional character known as a relative of Dino Brewster in the "Need for Speed" film universe.
  • C. Mary Sue Coleman
    Mary Sue Coleman is an American chemist and academic leader best known for serving as president of the University of Michigan and the University of Iowa and for her influential role in higher education policy.
  • D. Diane Bemus
    Diane Bemus is an individual whose birth name is Diane Bemus and who is also known as Diane Bemus Patrick.
  • E. Ann Coleman
    Ann Coleman was a key benefactor and restorer of France’s Château de Villandry, helping to preserve and revive the historic Renaissance estate and its renowned gardens.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fa1aac81908e4b86abedf295ca completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3b8fe488190b9155100c647a948 completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:50 a.m.