Triple
T22828968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Pan (2003 film) |
E565743
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Michael Darling |
—
|
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: Michael Darling | Statement: [Peter Pan (2003 film), character, Michael Darling]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Darling Context triple: [Peter Pan (2003 film), character, Michael Darling]
-
A.
Michael Darling
chosen
Michael Darling is the youngest of the Darling children in J.M. Barrie’s Peter Pan, known for his innocence, curiosity, and adventures in Neverland alongside his siblings and the Lost Boys.
-
B.
Joe Dougherty
Joe Dougherty was an American voice actor best known for originating the voice of the Warner Bros. cartoon character Porky Pig in the 1930s.
-
C.
Dev Jennings
Dev Jennings was an American cinematographer known for his work on early 20th-century films, including influential crime dramas of the 1930s.
-
D.
Martin Dillon
Martin Dillon is an Irish journalist and author renowned for his investigative books on the Northern Ireland Troubles and paramilitary violence.
-
E.
Phil Morrow
Phil Morrow is a television producer known for his work in developing and producing various entertainment and factual programs.
- 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_69e24585ab1c81909b2b5065d15805d5 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e2a0e308190941064965346f890 |
completed | April 29, 2026, 3:42 a.m. |
Created at: April 17, 2026, 3:34 p.m.