Triple
T15742142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Ramsey |
E381625
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Joan Hamilton |
E780009
|
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: Joan Hamilton | Statement: [Michael Ramsey, spouse, Joan Hamilton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan Hamilton Context triple: [Michael Ramsey, spouse, Joan Hamilton]
-
A.
Joan Hamilton
chosen
Joan Hamilton is known as the spouse of Michael Ramsey.
-
B.
Joan Graham
Joan Graham is known as the mother of American actress Heather Graham.
-
C.
Joan Bolger
Joan Bolger is the wife of former New Zealand Prime Minister Jim Bolger and served as the country's viceregal consort during his term as Governor-General.
-
D.
Joan Hackett
Joan Hackett was an American actress known for her acclaimed work in film, television, and theater during the 1960s and 1970s, often portraying complex, intelligent female characters.
-
E.
Joan Drane
Joan Drane was the wife of American actor Lee Van Cleef, known for his roles in classic Western films.
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fd97d6c8190b2fa6ca422bfe512 |
completed | April 16, 2026, 2:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00580789c08190994c5c71525aadc6 |
completed | May 10, 2026, 10:03 a.m. |
Created at: April 10, 2026, 4:46 a.m.