Triple
T19887414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Kent |
E477936
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Caravan |
E1354277
|
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: Caravan | Statement: [Jean Kent, notableWork, Caravan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caravan Context triple: [Jean Kent, notableWork, Caravan]
-
A.
Caravan
Caravan is a single-engine turboprop utility aircraft produced by Cessna, widely used for regional passenger, cargo, and bush operations.
-
B.
Caravan
"Caravan" is a famous jazz standard composed in 1936, closely associated with Duke Ellington’s orchestra and known for its exotic, Latin-tinged harmonies and rhythms.
-
C.
Caravan
chosen
Caravan is a 1946 British drama film directed by Arthur Crabtree, known for its romantic adventure plot set across Spain and England.
-
D.
Karawane
Karawane is a famous sound poem by Dadaist artist Hugo Ball, known for its nonsensical syllables and performance in Zurich’s Cabaret Voltaire.
-
E.
Caravan to Vaccarès
Caravan to Vaccarès is a 1970 thriller novel by Alistair MacLean set in the south of France, involving intrigue, danger, and a deadly conspiracy surrounding a group of Gypsies.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590b12c08190bf44a3f3b2cb9122 |
completed | April 20, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07dbd16ff08190b03caa3b20478ef4 |
completed | May 16, 2026, 2:52 a.m. |
Created at: April 10, 2026, 1:52 p.m.