Triple
T5303091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James M. McPherson |
E120029
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Patricia McPherson
Patricia McPherson is the wife of Pulitzer Prize–winning Civil War historian James M. McPherson.
|
E691260
|
NE FINISHED |
How this triple was built (4 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: Patricia McPherson | Statement: [James M. McPherson, spouse, Patricia McPherson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patricia McPherson Context triple: [James M. McPherson, spouse, Patricia McPherson]
-
A.
Patricia Conolly
Patricia Conolly is an Australian-born stage actress known for her extensive work on Broadway and in major theatre productions internationally.
-
B.
Patricia Scott
Patricia Scott was the first wife of acclaimed film and theater director Mike Nichols.
-
C.
Patricia Gaul
Patricia Gaul is an American character actress known for her supporting roles in films such as "The Big Chill," "Silverado," and "Road Trip."
-
D.
Patricia Hodgson
Patricia Hodgson is a British media executive and regulator known for senior roles at the BBC and as chair of Ofcom.
-
E.
Patricia O’Callaghan
Patricia O’Callaghan is a Canadian soprano and cabaret-style singer known for her interpretations of Leonard Cohen’s songs and eclectic repertoire spanning classical, pop, and chanson.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Patricia McPherson Triple: [James M. McPherson, spouse, Patricia McPherson]
Generated description
Patricia McPherson is the wife of Pulitzer Prize–winning Civil War historian James M. McPherson.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Patricia McPherson Target entity description: Patricia McPherson is the wife of Pulitzer Prize–winning Civil War historian James M. McPherson.
-
A.
Patricia Conolly
Patricia Conolly is an Australian-born stage actress known for her extensive work on Broadway and in major theatre productions internationally.
-
B.
Patricia Scott
Patricia Scott was the first wife of acclaimed film and theater director Mike Nichols.
-
C.
Patricia Gaul
Patricia Gaul is an American character actress known for her supporting roles in films such as "The Big Chill," "Silverado," and "Road Trip."
-
D.
Patricia Hodgson
Patricia Hodgson is a British media executive and regulator known for senior roles at the BBC and as chair of Ofcom.
-
E.
Patricia O’Callaghan
Patricia O’Callaghan is a Canadian soprano and cabaret-style singer known for her interpretations of Leonard Cohen’s songs and eclectic repertoire spanning classical, pop, and chanson.
- F. None of above. chosen
Provenance (5 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_69bd44704be88190acdb2ac481b0ff55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd851b685c8190b7ed8c762a807395 |
completed | March 20, 2026, 5:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9742fd0dc8190a154cf83c87eb508 |
completed | March 29, 2026, 6:49 p.m. |
| NEDg | Description generation | batch_69c9751e5e148190bf238d825501eccb |
completed | March 29, 2026, 6:53 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c9756a07088190a3bda04eb31016ea |
completed | March 29, 2026, 6:54 p.m. |
Created at: March 20, 2026, 1:53 p.m.