Triple
T9535456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Lawford |
E230002
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mary Rowan |
E230002
|
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: Mary Rowan | Statement: [Peter Lawford, spouse, Mary Rowan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Rowan Context triple: [Peter Lawford, spouse, Mary Rowan]
-
A.
Mary Rowan
chosen
Mary Rowan was the wife of British-American actor and Rat Pack member Peter Lawford.
-
B.
Sarah Child
Sarah Child was an English heiress from the prominent Child banking family who became Countess of Westmorland through her marriage into the British aristocracy.
-
C.
Mary Ure
Mary Ure was a Scottish stage and film actress best known for her acclaimed performances in works like "Look Back in Anger" and "Sons and Lovers."
-
D.
Jemima Frances Meikle
Jemima Frances Meikle was the wife of Canadian architect and civil engineer John George Howard, noted as his lifelong partner during his career in 19th-century Toronto.
-
E.
Mary Jones
Mary Jones is an actress known for appearing in screen productions alongside Ms. Weiss.
- 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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98cd6a5c8190835c0910ec38ede3 |
completed | April 1, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c4804988190b99343734b4882e0 |
completed | April 4, 2026, 5:37 p.m. |
Created at: March 30, 2026, 8 p.m.