Triple
T11878380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter and the Starcatcher |
E282588
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Smee |
E339882
|
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: Smee | Statement: [Peter and the Starcatcher, featuresCharacter, Smee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Smee Context triple: [Peter and the Starcatcher, featuresCharacter, Smee]
-
A.
Mr. Smee
chosen
Mr. Smee is the bumbling yet kind-hearted boatswain and loyal sidekick to Captain Hook in J.M. Barrie’s Peter Pan stories.
-
B.
Skully
Skully is a small, talkative green parrot who serves as a lookout and helpful companion to the young pirate crew in the children's animated series "Jake and the Never Land Pirates."
-
C.
Jobu
Jobu is the fictional voodoo deity that baseball player Pedro Cerrano prays to for help with his hitting in the film "Major League."
-
D.
Wanz
Wanz is an American singer best known for providing the soulful hook on Macklemore & Ryan Lewis's hit single "Thrift Shop."
-
E.
Tark the Shark
Tark the Shark is the famous nickname of Hall of Fame college basketball coach Jerry Tarkanian, known for his successful and often controversial tenure at UNLV.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8be1b6a5c81909a18c54205dda09c |
completed | April 10, 2026, 9:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281d8c65081908ebaf4bff5670c47 |
completed | April 29, 2026, 10:10 p.m. |
Created at: April 8, 2026, 9:44 p.m.