Triple
T20461256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christian Sebaldt |
E501927
|
entity |
| Predicate | roleInResidentEvilApocalypse |
P140183
|
FINISHED |
| Object | director of photography |
—
|
LITERAL 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: director of photography | Statement: [Christian Sebaldt, roleInResidentEvilApocalypse, director of photography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInResidentEvilApocalypse Context triple: [Christian Sebaldt, roleInResidentEvilApocalypse, director of photography]
-
A.
roleInDisasterMovie
Indicates that an entity has a specific acting or production role in a disaster-themed movie.
-
B.
roleInRescue
Indicates the specific function or responsibility an entity has within a rescue operation or event.
-
C.
roleInBeastsOfNoNation
Indicates that an entity has a role or participation in the film "Beasts of No Nation."
-
D.
roleInElysium
Indicates that an entity holds a specific role, position, or function within the context of Elysium.
-
E.
roleInCitadel
Indicates the specific function, position, or responsibility an entity holds within a citadel or fortified complex.
- F. None of above. chosen
Provenance (4 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e696a642648190808709020f91122b |
completed | April 20, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69e57679eb40819086142df3e39c928e |
completed | April 20, 2026, 12:42 a.m. |
| PDg | Predicate description generation | batch_69e58d766b408190a1d3698145fb6d30 |
completed | April 20, 2026, 2:20 a.m. |
Created at: April 16, 2026, 11:33 a.m.