Triple
T29115595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Infernal Affairs II |
E737036
|
entity |
| Predicate | exploresBackstoryOf |
P115645
|
FINISHED |
| Object | Lau Kin-ming |
—
|
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: Lau Kin-ming | Statement: [Infernal Affairs II, exploresBackstoryOf, Lau Kin-ming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exploresBackstoryOf Context triple: [Infernal Affairs II, exploresBackstoryOf, Lau Kin-ming]
-
A.
expandsBackstoryOf
chosen
Indicates that one entity provides additional background details or context that elaborate on the history or origins of another entity.
-
B.
chronologicalBackstoryIn
Indicates that one event or narrative element serves as a prior backstory that occurs earlier in time within the timeline of another event or narrative.
-
C.
historicalExploration
Indicates that an entity has engaged in or is associated with the act of exploring or investigating something in the past.
-
D.
originStoryIncludes
Indicates that an entity’s origin story contains, involves, or features the referenced element as a component or part of that backstory.
-
E.
hasFictionalBackstory
Indicates that an entity is associated with an invented or imaginary narrative background rather than a real-world history.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f69383222c81909d8baa04129d5c81 |
completed | May 3, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 28, 2026, 11:22 a.m.