Triple
T32657144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terwilliger |
E834892
|
entity |
| Predicate | notableBearerRoleType |
P203466
|
FINISHED |
| Object | recurring villain |
—
|
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: recurring villain | Statement: [Terwilliger, notableBearerRoleType, recurring villain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBearerRoleType Context triple: [Terwilliger, notableBearerRoleType, recurring villain]
-
A.
notableBearerDescription
Indicates that the subject has a notable bearer, with the object providing a textual description of that bearer’s significance or identity.
-
B.
notableBearerOfRole
chosen
Indicates that an entity is a particularly prominent or well-known holder or performer of a specified role.
-
C.
notableBearerVariantOf
Indicates that one entity is a notable or prominent variant or version of another entity that bears or carries its characteristics.
-
D.
notableBearerRelative
Indicates that one entity is a notable person who is related (by family or kinship) to the bearer of another entity, such as a title, name, or distinction.
-
E.
notableBearerExecutedBy
Indicates that a notable holder or bearer of something was executed by a specified agent or authority.
- 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_69f3492f72248190ba42fa596aea50e1 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:08 a.m.