Triple
T18629362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat Conroy |
E455368
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Donald Conroy |
—
|
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: Donald Conroy | Statement: [Pat Conroy, parent, Donald Conroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Conroy Context triple: [Pat Conroy, parent, Donald Conroy]
-
A.
Donald Patrick Conroy
chosen
Donald Patrick Conroy was an American author best known for his emotionally powerful novels set in the American South, including "The Prince of Tides" and "The Great Santini."
-
B.
Paul Conroy
Paul Conroy is the fictional American truck driver who becomes trapped in a coffin underground in the psychological thriller film "Buried."
-
C.
Jeff Conroy
Jeff Conroy is a television producer best known for his executive production work on the reality series "Storage Wars."
-
D.
Edward Connelly
Edward Connelly was an American character actor of the silent film era, known for his supporting roles in numerous early Hollywood productions.
-
E.
Jack Conroy
Jack Conroy is a cinematographer best known for his work on the acclaimed film "My Left Foot."
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f06f4a081909b64f33814577488 |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.