Triple
T8278706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dumb and Dumber |
E193610
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Mike Starr |
E36957
|
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: Mike Starr | Statement: [Dumb and Dumber, starring, Mike Starr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike Starr Context triple: [Dumb and Dumber, starring, Mike Starr]
-
A.
Mike Starr
chosen
Mike Starr is an American character actor known for his imposing presence and frequent roles as tough guys or mobsters in films and television.
-
B.
Mike Starr
Mike Starr was an American bassist best known as the original bass player for the Seattle grunge band Alice in Chains.
-
C.
Ron Starr
Ron Starr is an American actor best known for his role in the classic Western film "Ride the High Country."
-
D.
Mike Starrs
Mike Starrs is a Scottish rock singer best known for his work with bands such as Colosseum II and Lucifer's Friend in the 1970s.
-
E.
Mike Krieger
Mike Krieger is a Brazilian-American entrepreneur and software engineer best known as the co-founder and former CTO of the photo-sharing social media platform Instagram.
- 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_69ca82e217a48190880695635c44b2ed |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb79ebb6b88190bc777b8bd72fcdbc |
completed | March 31, 2026, 7:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd6863c22c8190b888a23bb9005712 |
completed | April 1, 2026, 6:48 p.m. |
Created at: March 30, 2026, 5:51 p.m.