Triple
T24687581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Dudley Harmon |
E611340
|
entity |
| Predicate | MarkHarmonOccupation |
P156982
|
FINISHED |
| Object | actor |
—
|
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: actor | Statement: [Thomas Dudley Harmon, MarkHarmonOccupation, actor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MarkHarmonOccupation Context triple: [Thomas Dudley Harmon, MarkHarmonOccupation, actor]
-
A.
Richard YoungOccupation
Indicates that Richard Young has or held a particular occupation or job role.
-
B.
leadActorOccupation
Indicates that the occupation specified is the primary professional role of the lead actor in a given work or context.
-
C.
Dan HartRole
Indicates that Dan Hart holds or performs a specific role, position, or function in relation to another entity or context.
-
D.
AlbertBrooksRole
Indicates that an entity represents a role or character played by Albert Brooks in a work.
-
E.
developerOfWorkAppearingIn
Indicates that one entity is the creator or developer of a work in which another entity appears or is featured.
- 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_69e2c4d678b081908910f4271627a31a |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
| PDg | Predicate description generation | batch_69f410fc18808190b4e47d5a71d3a126 |
completed | May 1, 2026, 2:33 a.m. |
Created at: April 18, 2026, 3:19 a.m.