Triple
T17026121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martial Law |
E413066
|
entity |
| Predicate | basedInPartOnStarPersonaOf |
P95156
|
FINISHED |
| Object | Sammo Hung |
—
|
NE NERFINISHED |
How this triple was built (3 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: Sammo Hung | Statement: [Martial Law, basedInPartOnStarPersonaOf, Sammo Hung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sammo Hung Context triple: [Martial Law, basedInPartOnStarPersonaOf, Sammo Hung]
-
A.
Sammo Hung Kam-bo
chosen
Sammo Hung Kam-bo is a renowned Hong Kong actor, martial artist, director, and action choreographer known for his influential work in martial arts cinema and collaborations with Jackie Chan.
-
B.
Yuen Biao
Yuen Biao is a Hong Kong martial artist and actor best known for his acrobatic kung fu performances and frequent collaborations with Jackie Chan and Sammo Hung in classic action films.
-
C.
Gordon Liu
Gordon Liu is a renowned Hong Kong martial arts actor and kung fu film star, best known for classics like "The 36th Chamber of Shaolin" and his roles in Quentin Tarantino's "Kill Bill" films.
-
D.
Yuen Woo-ping
Yuen Woo-ping is a renowned Hong Kong martial arts choreographer and film director best known for his influential action work in classics like "Drunken Master," "The Matrix" trilogy, and "Crouching Tiger, Hidden Dragon."
-
E.
Jackie Chan
Jackie Chan is a Hong Kong martial artist, actor, stuntman, and filmmaker renowned worldwide for his acrobatic fighting style, innovative stunts, and blend of action and comedy in films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedInPartOnStarPersonaOf Context triple: [Martial Law, basedInPartOnStarPersonaOf, Sammo Hung]
-
A.
stagePersonaOf
Indicates a relationship where one entity is the staged or performed persona, role, or character representation of another entity.
-
B.
basedOnStarPowerOf
chosen
Indicates that something is determined, influenced, or derived from the star power (e.g., fame, popularity, or celebrity status) of an entity.
-
C.
protagonistBasedOn
Indicates that a fictional work’s main character is modeled on, inspired by, or derived from a particular real or fictional person or entity.
-
D.
characterBasedOn
Indicates that one character is modeled, inspired, or derived from another real or fictional entity.
-
E.
associatedPerformerPersona
Indicates a relationship where a performer is linked to a specific persona or role identity they adopt in their performances.
- F. None of above.
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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d46a5081908bc5681621dd8534 |
completed | April 18, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_69e35d5be7f48190af9db67a1e23850f |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.