Triple
T35859063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Floyd the pig |
E1036591
|
entity |
| Predicate | hasLikenessUsedIn |
P198023
|
FINISHED |
| Object | Floyd of Rosedale trophy |
—
|
NE NERFINISHED |
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: Floyd of Rosedale trophy | Statement: [Floyd the pig, hasLikenessUsedIn, Floyd of Rosedale trophy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLikenessUsedIn Context triple: [Floyd the pig, hasLikenessUsedIn, Floyd of Rosedale trophy]
-
A.
hasPersonaUsedIn
Indicates that a particular persona is employed or applied within a given context, system, or interaction.
-
B.
hasPhotographicAppearanceIn
Indicates that one entity appears in a photograph or photographic representation associated with another entity.
-
C.
hasHumanUse
Indicates that something is used, employed, or utilized by humans for a particular purpose or benefit.
-
D.
appearanceInImages
Indicates that an entity is visually present or depicted within one or more images.
-
E.
usedOwnFaceAsModelFor
Indicates that an entity created or designed something using their own face as the reference or template.
- 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_69f76e1b4aa481909630373171eb5ec6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fec25f0fc48190b87ab1f9cd1eb0de |
completed | May 9, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69fec079a770819098df7cc3049df954 |
completed | May 9, 2026, 5:04 a.m. |
| PDg | Predicate description generation | batch_69fec25e3d708190be27135c57b189a5 |
completed | May 9, 2026, 5:13 a.m. |
Created at: May 3, 2026, 4:06 p.m.