Triple
T11009228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dick Haymes |
E260202
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Joanne Dru |
E353298
|
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: Joanne Dru | Statement: [Dick Haymes, spouse, Joanne Dru]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joanne Dru Context triple: [Dick Haymes, spouse, Joanne Dru]
-
A.
Joanne Dru
chosen
Joanne Dru was an American film and television actress best known for her roles in classic Westerns and dramas of the 1940s and 1950s.
-
B.
Colleen Sharp
Colleen Sharp is a film editor best known for her work on Terrence Malick’s acclaimed drama "Days of Heaven."
-
C.
Anne Rennie
Anne Rennie is known as the wife of bestselling adventure novelist Wilbur Smith.
-
D.
Annette Kirk
Annette Kirk is an American cultural advocate and widow of conservative thinker Russell Kirk, known for promoting his intellectual legacy and traditionalist ideas through institutions such as the Kirk Center for Cultural Renewal.
-
E.
Lisa Blount
Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7978810208190b8e2966ae67b6314 |
completed | April 9, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4acc9d60c819084e342076fe682fc |
completed | April 19, 2026, 10:22 a.m. |
Created at: April 8, 2026, 9:25 p.m.