Triple

T22128035
Position Surface form Disambiguated ID Type / Status
Subject The House That Built Me E546839 entity
Predicate writer P1360 FINISHED
Object Tom Douglas 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: Tom Douglas | Statement: [The House That Built Me, writer, Tom Douglas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Douglas
Context triple: [The House That Built Me, writer, Tom Douglas]
  • A. Tom Douglas chosen
    Tom Douglas is an American country music songwriter known for penning numerous hit songs for major Nashville artists.
  • B. Michael Lee
    Michael Lee is a young, intelligent, and increasingly ruthless drug dealer from the television series "The Wire," whose rise in West Baltimore’s drug trade reflects the cycle of violence and limited choices facing inner-city youth.
  • C. Mike Donnelly
    Mike Donnelly is the well-meaning but accident-prone protagonist of the comedy film "Black Sheep," whose misadventures jeopardize his brother’s political campaign.
  • D. Mark Kilmer
    Mark Kilmer is the brother of American actor Val Kilmer and a member of the Kilmer family, which has ties to the entertainment industry.
  • E. Michael R. Miller
    Michael R. Miller is a film editor known for his work on the 1999 supernatural horror film "Stigmata."
  • 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_69e11e39bf348190b541bfa16a7b71e0 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12982eaa08190933d3036c020f562 completed April 28, 2026, 9:41 p.m.
Created at: April 16, 2026, 8:32 p.m.