Triple
T10635289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michelle Pfeiffer |
E250563
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | David E. Kelley |
E275829
|
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: David E. Kelley | Statement: [Michelle Pfeiffer, spouse, David E. Kelley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David E. Kelley Context triple: [Michelle Pfeiffer, spouse, David E. Kelley]
-
A.
David E. Kelley
chosen
David E. Kelley is an American television writer and producer known for creating and producing acclaimed legal and drama series such as Ally McBeal, The Practice, and Big Little Lies.
-
B.
David Shore
David Shore is a Canadian television writer and producer best known for creating the medical drama series "House."
-
C.
Graham Yost
Graham Yost is an American screenwriter, producer, and showrunner best known for creating the TV series "Justified" and writing the film "Speed."
-
D.
Eric Lange
Eric Lange is an American character actor known for his roles in television series such as Victorious, Lost, and Narcos.
-
E.
Ira Steven Behr
Ira Steven Behr is an American television producer and writer best known for his work as showrunner on Star Trek: Deep Space Nine and contributions to other genre series.
- 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_69d6aa5993448190a493b790b8f85010 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfac70f481908363f9ac0b651fbe |
completed | April 8, 2026, 11:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d96bc57a8081908abd73f4273d0666 |
completed | April 10, 2026, 9:29 p.m. |
Created at: April 8, 2026, 9:03 p.m.