Triple
T18856359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Buchanan |
E461178
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Karen Hayes |
—
|
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: Karen Hayes | Statement: [Bill Buchanan, spouse, Karen Hayes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karen Hayes Context triple: [Bill Buchanan, spouse, Karen Hayes]
-
A.
Karen Hayes
chosen
Karen Hayes is a fictional intelligence analyst and later director at the Counter Terrorist Unit (CTU) in the television series "24."
-
B.
Laura Hayes
Laura Hayes is an American actress and comedian best known for her role in the ensemble cast of the film "Beauty Shop."
-
C.
Kate Fahy
Kate Fahy is a British actress and theatre director known for her extensive stage work and long-term partnership with actor Jonathan Pryce.
-
D.
Bridget Hayward
Bridget Hayward is the daughter of acclaimed American actress Margaret Sullavan and producer Leland Hayward.
-
E.
Kate Hennessy
Kate Hennessy is an American writer and the granddaughter of Catholic social activist Dorothy Day, known for her memoirs and work chronicling her family’s legacy.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05d0bb8819094d0447441f85b57 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 10, 2026, 11:57 a.m.