Triple
T7022730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Ring |
E162866
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Craig Wood |
E303054
|
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: Craig Wood | Statement: [The Ring, editor, Craig Wood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craig Wood Context triple: [The Ring, editor, Craig Wood]
-
A.
Craig Wood
chosen
Craig Wood is a film editor best known for his work on major Hollywood blockbusters, including entries in the Pirates of the Caribbean franchise.
-
B.
John Morris
John Morris is an American voice actor best known for voicing Andy Davis in the Toy Story film series.
-
C.
John Morris
John Morris is a film producer best known for his work on mainstream Hollywood comedies, including the family sequel "Daddy's Home 2."
-
D.
Ray Wood
Ray Wood was an English footballer for Manchester United who survived the 1958 Munich air disaster.
-
E.
D. Woods
D. Woods is an American singer, dancer, and actress best known as a former member of the pop/R&B girl group Danity Kane.
- 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_69c6885b26248190a857541e3d10e299 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e1edf3608190b7ba0bfb85710e97 |
completed | March 27, 2026, 8 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7757c87788190b09ced669b5c4d83 |
completed | March 28, 2026, 6:30 a.m. |
Created at: March 27, 2026, 2:35 p.m.