Triple
T12009470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turn |
E285868
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Caleb Brewster |
E285864
|
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: Caleb Brewster | Statement: [Turn, mainCharacter, Caleb Brewster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caleb Brewster Context triple: [Turn, mainCharacter, Caleb Brewster]
-
A.
Caleb Brewster
chosen
Caleb Brewster was a real-life American Revolutionary War soldier and daring whaleboat captain who served as a key courier in George Washington’s Culper Spy Ring.
-
B.
Caleb Jackson
Caleb Jackson is known primarily as the son of American actor and activist Jonathan Jackson.
-
C.
Caleb Colton
Caleb Colton is the young drifter-turned-reluctant vampire protagonist of the 1987 cult horror film "Near Dark," whose struggle with his new undead nature drives the movie’s central conflict.
-
D.
Caleb Lyon
Caleb Lyon was a 19th-century American politician and designer best known for creating the Great Seal of the State of California.
-
E.
Caleb Strong
Caleb Strong was an American lawyer and statesman who served as a U.S. Senator and twice as Governor of Massachusetts in the early years of the United States.
- 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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903d61a4c81909e6cb6500b61df94 |
completed | April 10, 2026, 2:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a5ccac481908c61fc1109cc6ef6 |
completed | May 2, 2026, 2:29 p.m. |
Created at: April 8, 2026, 9:46 p.m.