Triple
T8607437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Devil Horse |
E203834
|
entity |
| Predicate | basedInMedium |
P18027
|
FINISHED |
| Object | cinema |
—
|
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: cinema | Statement: [The Devil Horse, basedInMedium, cinema]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedInMedium Context triple: [The Devil Horse, basedInMedium, cinema]
-
A.
basedOnMedium
Indicates that one entity is derived from, adapted from, or created using another entity as its source medium or foundational material.
-
B.
occursInMedium
Indicates that an event, process, or interaction takes place within or is hosted by a particular medium or environment.
-
C.
introducedInMedium
chosen
Indicates that an entity first appears or is initially presented within a specified medium (such as a book, film, game, or other format).
-
D.
subsequentMedium
Indicates that one medium or format follows another in a sequence, typically as a later or alternative form of the same content or communication.
-
E.
representsMedium
Indicates that one entity serves as the medium, channel, or means through which another entity is expressed, communicated, or realized.
- 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_69ca832c23e4819095a9f3eea4a21828 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46ec301881908ce148a3f07069fe |
completed | March 31, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69cc454eb2908190acf0e4336bc67e7b |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:25 p.m.