Triple
T33517793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piranha |
E858413
|
entity |
| Predicate | popularMediaPortrayal |
P106633
|
FINISHED |
| Object | man-eating fish |
—
|
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: man-eating fish | Statement: [Piranha, popularMediaPortrayal, man-eating fish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: popularMediaPortrayal Context triple: [Piranha, popularMediaPortrayal, man-eating fish]
-
A.
media depiction
chosen
Indicates that one entity visually or narratively represents, portrays, or illustrates another entity in some form of media.
-
B.
isPopularInMedia
Indicates that an entity is frequently featured, referenced, or well-liked across various media channels or platforms.
-
C.
portraysFictionalized
Indicates that one entity represents or depicts another entity in a fictionalized or altered manner, rather than as a strictly accurate portrayal.
-
D.
portrayalRecognition
Indicates that one entity recognizes or identifies another entity as a portrayal or representation of a particular subject or character.
-
E.
culturalDepictionBy
Indicates that one entity serves as the creator or source of a cultural representation or portrayal of another entity.
- 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_69f349781c6c819082c516b260efe7e2 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 1, 2026, 1:39 a.m.