Triple
T10973255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manu Bennett |
E259300
|
entity |
| Predicate | playedCharacter |
P1507
|
FINISHED |
| Object | Crixus |
E429710
|
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: Crixus | Statement: [Manu Bennett, playedCharacter, Crixus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crixus Context triple: [Manu Bennett, playedCharacter, Crixus]
-
A.
Crixus
chosen
Crixus is a prominent gladiator character in the television series "Spartacus: Blood and Sand," known for his fierce combat skills and complex, prideful nature.
-
B.
Clytius
Clytius is a lesser-known Trojan prince in Greek mythology, one of the many sons of King Priam of Troy.
-
C.
Aufidius
Aufidius is a Volscian general and the chief military rival of the Roman hero in William Shakespeare’s tragedy "Coriolanus."
-
D.
Sebastos
Sebastos was the grand artificial harbor of ancient Caesarea Maritima, renowned as one of the largest and most advanced seaports of the Roman world.
-
E.
Euphorbus
Euphorbus is a Trojan warrior in Greek mythology, noted for wounding Patroclus during the Trojan War before the latter was finally slain.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7719c16648190ab5a87abb1c61990 |
completed | April 9, 2026, 9:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d7a0b3dc819084fbda3227caf5b5 |
completed | April 18, 2026, 1 a.m. |
Created at: April 8, 2026, 9:24 p.m.