Triple
T19386751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Women Talking |
E484955
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Christopher Donaldson |
—
|
NE NERFINISHED |
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: Christopher Donaldson | Statement: [Women Talking, editor, Christopher Donaldson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christopher Donaldson Context triple: [Women Talking, editor, Christopher Donaldson]
-
A.
Christopher Donaldson
chosen
Christopher Donaldson is a film editor known for his work on David Cronenberg’s 2022 science fiction body horror film "Crimes of the Future."
-
B.
David Scearce
David Scearce is a Canadian screenwriter best known for adapting Christopher Isherwood’s novel into the acclaimed film "A Single Man."
-
C.
Dave Dorman
Dave Dorman is an American illustrator best known for his detailed and dynamic science fiction and fantasy artwork, particularly his Star Wars paintings and comic book covers.
-
D.
Christopher De Vore
Christopher De Vore is an American screenwriter best known for co-writing the acclaimed 1980 film "The Elephant Man."
-
E.
Steven Dillingham
Steven Dillingham is an American government official who served as Director of the U.S. Census Bureau during the 2020 United States census.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b40d1148190b4fcd9ad56aa6910 |
completed | April 20, 2026, 12:25 p.m. |
Created at: April 10, 2026, 1:36 p.m.