Triple
T15515978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Two of a Kind |
E368834
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Richard Bright |
E1161988
|
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: Richard Bright | Statement: [Two of a Kind, hasCastMember, Richard Bright]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Bright Context triple: [Two of a Kind, hasCastMember, Richard Bright]
-
A.
Richard Bright
Richard Bright was a 19th-century English physician best known as a pioneer of nephrology for his landmark work on kidney disease.
-
B.
Richard Bright
chosen
Richard Bright was an American character actor best known for his role as Al Neri in "The Godfather" film trilogy.
-
C.
William Cleland
William Cleland was a Scottish Covenanter and soldier known for leading the Cameronian regiment in late 17th-century conflicts against Jacobite forces.
-
D.
Philip Christison
Philip Christison was a British Army general who held senior commands in World War II, particularly in Southeast Asia.
-
E.
Richard Sharp
Richard Sharp is a British businessman and former investment banker best known for serving as chairman of the BBC.
- 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_69d85a1794cc8190b0b428716296e63e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e04033303c8190a87b6384f68a6921 |
completed | April 16, 2026, 1:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff454eafe48190a481b4adb8388395 |
completed | May 9, 2026, 2:31 p.m. |
Created at: April 10, 2026, 4:02 a.m.