Triple
T14904763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Hurt |
E360099
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Anwen Rees-Myers |
E290383
|
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: Anwen Rees-Myers | Statement: [John Hurt, spouse, Anwen Rees-Myers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anwen Rees-Myers Context triple: [John Hurt, spouse, Anwen Rees-Myers]
-
A.
Anwen Rees-Myers
chosen
Anwen Rees-Myers is a British film producer and the widow of acclaimed actor John Hurt.
-
B.
Anwen Williams
Anwen Williams is the daughter of Gwen Cooper, a central character from the British science fiction series Torchwood.
-
C.
Maia Rindell
Maia Rindell is a young lawyer whose career and personal life are upended by a massive financial scandal involving her family in the legal drama series "The Good Fight."
-
D.
Tamsyn Muir
Tamsyn Muir is a New Zealand author best known for her Locked Tomb series, which blends science fantasy, necromancy, and dark humor.
-
E.
Melanie Reeve
Melanie Reeve is the wife of American filmmaker Matt Reeves, known for her long-term partnership with the director behind films like Cloverfield and The Batman.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded60cd5588190b1efecc2b220da69 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72b4e4f88190af7e859d93dbbd28 |
completed | May 8, 2026, 11:33 p.m. |
Created at: April 10, 2026, 2:12 a.m.