Triple
T37374639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Brock |
E927941
|
entity |
| Predicate | mediumOfNotability |
P102251
|
FINISHED |
| Object | film |
—
|
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: film | Statement: [Ray Brock, mediumOfNotability, film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumOfNotability Context triple: [Ray Brock, mediumOfNotability, film]
-
A.
mediumOfFame
chosen
Indicates the medium, field, or domain through which an entity became famous or gained public recognition.
-
B.
notableMedia
Indicates a relationship where a media work is recognized as significant, prominent, or especially relevant in connection with a given entity.
-
C.
mediumOfRecord
Indicates the primary medium or format through which an event, work, or information is officially documented or recorded.
-
D.
notableAudience
Indicates that an entity is especially well-known, relevant, or targeted among a particular audience or group of people.
-
E.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.