Triple
T18819547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Kemp |
E460225
|
entity |
| Predicate | hasMadeDocumentaryAbout |
P40239
|
FINISHED |
| Object | male suicide and mental health |
—
|
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: male suicide and mental health | Statement: [Roman Kemp, hasMadeDocumentaryAbout, male suicide and mental health]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMadeDocumentaryAbout Context triple: [Roman Kemp, hasMadeDocumentaryAbout, male suicide and mental health]
-
A.
hasDocumentaryAboutIt
Indicates that there exists a documentary film or program whose subject matter is focused on the referenced entity.
-
B.
madeDocumentary
chosen
Indicates that one entity created or produced a documentary film or program about another entity.
-
C.
hasLiveActionFilm
Indicates that a subject has a corresponding live-action film adaptation or representation.
-
D.
hasNotableFilm
Indicates that an entity is associated with a film that is considered significant, well-known, or particularly noteworthy.
-
E.
hasRemadeOwnFilm
Indicates that a filmmaker has created a new version or remake of a film they previously made themselves.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6b8b7d88190a8828746176776ea |
completed | April 20, 2026, 4:08 a.m. |
| PD | Predicate disambiguation | batch_69e48d1b10ec8190985c6fb5766ff981 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:55 a.m.