Triple
T17891082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albert Romolo Broccoli |
E447316
|
entity |
| Predicate | coFounderOf |
P104
|
FINISHED |
| Object | Danjaq |
—
|
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: Danjaq | Statement: [Albert Romolo Broccoli, coFounderOf, Danjaq]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Danjaq Context triple: [Albert Romolo Broccoli, coFounderOf, Danjaq]
-
A.
Danjaq
chosen
Danjaq is the film production and rights-holding company best known for owning and controlling the James Bond movie franchise.
-
B.
Galantis
Galantis is a Swedish electronic dance music duo known for their melodic, festival-ready house tracks and global hits like "Runaway (U & I)."
-
C.
Dunbeg
Dunbeg is a small coastal village in Argyll and Bute on Scotland’s west coast, known for its proximity to Oban and its scenic Highland surroundings.
-
D.
Madeon
Madeon is a French electronic music producer and DJ known for his intricate, melodic dance tracks and collaborations with artists like Porter Robinson.
-
E.
Kalafina
Kalafina is a Japanese female vocal group known for their rich harmonies and frequent contributions to anime soundtracks.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7948888190b59ddc7061d13e84 |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:18 a.m.