Triple
T2965021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikael Salomon |
E80140
|
entity |
| Predicate | workedOnAs |
P4325
|
FINISHED |
| Object | The Abyss – cinematographer |
—
|
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: The Abyss – cinematographer | Statement: [Mikael Salomon, workedOnAs, The Abyss – cinematographer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedOnAs Context triple: [Mikael Salomon, workedOnAs, The Abyss – cinematographer]
-
A.
workedUnder
Indicates that one entity was hierarchically subordinate to and performed work under the supervision or authority of another entity.
-
B.
workedAs
chosen
Indicates that an entity held a particular job, role, or position, performing work in that capacity.
-
C.
hasWorkedFor
Indicates that an entity has been employed by or has provided work or services to another entity.
-
D.
hasWorkedIn
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
-
E.
workOn
Indicates that an agent is actively engaged in performing tasks or making progress on a particular project, object, or assignment.
- 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_69ad8b1341848190bd19dbf46892887d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9958b1e48190a77f37bf63333c5b |
completed | March 8, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69ad960e71f8819088179d11248c6ed0 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.