Triple
T23050081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaki Rostom |
E573984
|
entity |
| Predicate | characterTypeSpecialization |
P107007
|
FINISHED |
| Object | villains |
—
|
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: villains | Statement: [Zaki Rostom, characterTypeSpecialization, villains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterTypeSpecialization Context triple: [Zaki Rostom, characterTypeSpecialization, villains]
-
A.
mainCharacterSpecialization
Indicates the specific role, class, or area of expertise that the main character is focused on or specialized in.
-
B.
creatorSpecialization
Indicates the specific field, discipline, or area of expertise in which a creator primarily works or is specialized.
-
C.
portrayedAsSpecialization
Indicates that one entity is depicted or represented as a specialized or more specific version of another entity.
-
D.
hasFictionalSpecialization
chosen
Indicates that an entity’s area of focus, expertise, or role is within a fictional or imaginative domain rather than a real-world specialization.
-
E.
unitSpecialization
Indicates that one unit is a specialized or more specific version of another unit within a hierarchical or categorical relationship.
- 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_69e245b9c11481909d06c872214d21af |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1867b800881909fabf9dca994c9e7 |
completed | April 29, 2026, 4:18 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:54 p.m.