Triple
T23018279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disko Troop |
E573093
|
entity |
| Predicate | hasSon |
P6882
|
FINISHED |
| Object | Dan Troop |
—
|
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: Dan Troop | Statement: [Disko Troop, hasSon, Dan Troop]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Troop Context triple: [Disko Troop, hasSon, Dan Troop]
-
A.
Dan Troop
Dan Troop is a fictional character known as a close companion of Harvey Cheyne in Rudyard Kipling’s novel "Captains Courageous."
-
B.
Dan Troop
chosen
Dan Troop is a fictional character known as the son of Disko Troop in Rudyard Kipling’s sea-faring novel "Captains Courageous."
-
C.
Dan Talbot
Dan Talbot was an influential American film distributor and exhibitor known for championing foreign and independent cinema in the United States.
-
D.
Dean Tolson
Dean Tolson is a former American professional basketball player best known for his college career at the University of Arkansas and his time as a forward in the NBA during the 1970s.
-
E.
Brent Murch
Brent Murch is a film editor known for his work on animated features, including *My Little Pony: The Movie*.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.