Triple
T17621031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spartacus: Blood and Sand |
E429708
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Andy Whitfield |
—
|
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: Andy Whitfield | Statement: [Spartacus: Blood and Sand, hasCastMember, Andy Whitfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy Whitfield Context triple: [Spartacus: Blood and Sand, hasCastMember, Andy Whitfield]
-
A.
Andy Whitfield
chosen
Andy Whitfield was a Welsh-Australian actor best known for his lead role as the gladiator Spartacus in the television series "Spartacus: Blood and Sand."
-
B.
David Whiteley
David Whiteley is an actor known for appearing in the action thriller film "Killer Elite."
-
C.
Andrew Whitham
Andrew Whitham is a distinguished geoscientist recognized for his significant contributions to the field, as evidenced by his receipt of the William Smith Medal.
-
D.
Alex Wharton
Alex Wharton is a musician best known for his past role in the instrumental rock/metal band The Fucking Champs.
-
E.
Steve Whittaker
Steve Whittaker is a prominent human-computer interaction researcher known for his influential work on digital memory, communication, and information management, recognized with the SIGCHI Lifetime Achievement Award.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46d36074481909ee79e238841edf2 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 5:51 a.m.