Triple
T20598549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Jungle Book (1967 film) |
E506112
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Larry Clemmons |
—
|
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: Larry Clemmons | Statement: [The Jungle Book (1967 film), screenwriter, Larry Clemmons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larry Clemmons Context triple: [The Jungle Book (1967 film), screenwriter, Larry Clemmons]
-
A.
Larry Clemmons
chosen
Larry Clemmons was an American animator and screenwriter best known for his long career at Walt Disney Productions, where he contributed to the scripts of several classic animated films.
-
B.
Larry Douglas
Larry Douglas is an actor known for playing the character Lun Tha in the musical "The King and I."
-
C.
Larry Seiple
Larry Seiple is a former American football player best known as the versatile punter and occasional offensive contributor for the Miami Dolphins during their dominant early-1970s era.
-
D.
Larry DeWaay
Larry DeWaay is a film producer best known for his work on the action war film "The Dogs of War."
-
E.
Ray Colcord
Ray Colcord was an American record producer and composer best known for his work in rock music and for scoring numerous television shows.
- 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_69e0b4ba6ae88190af871e1f9522c704 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aa1e251c8190926dafe1402eb63c |
completed | April 20, 2026, 10:35 p.m. |
Created at: April 16, 2026, 11:40 a.m.