Triple
T33561952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benedict (Last Action Hero) |
E859645
|
entity |
| Predicate | eyeDetail |
P39138
|
FINISHED |
| Object | glass eye with interchangeable designs |
—
|
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: glass eye with interchangeable designs | Statement: [Benedict (Last Action Hero), eyeDetail, glass eye with interchangeable designs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyeDetail Context triple: [Benedict (Last Action Hero), eyeDetail, glass eye with interchangeable designs]
-
A.
eyeCharacteristic
Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
-
B.
eyeType
chosen
Indicates the specific kind or category of eyes an entity has, such as their form, structure, or visual style.
-
C.
eyeAssociation
Indicates a relationship where one entity is associated with, linked to, or characterized by a particular eye or eye-related feature of another entity.
-
D.
eyeFeatureObserved
Indicates that a specific characteristic or condition of the eye has been detected or recorded through observation.
-
E.
eyeLocation
Indicates the spatial position or placement of an eye relative to a reference object or coordinate system.
- 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_69f3497c1d288190a844ea699914e038 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f71372688190b83e34f05720367f |
completed | May 3, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:40 a.m.