Triple
T5706046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batman & Robin |
E125785
|
entity |
| Predicate | featuresPortrayalBy |
P49090
|
FINISHED |
| Object | George Clooney as Batman |
—
|
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: George Clooney as Batman | Statement: [Batman & Robin, featuresPortrayalBy, George Clooney as Batman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresPortrayalBy Context triple: [Batman & Robin, featuresPortrayalBy, George Clooney as Batman]
-
A.
portrayalFeature
chosen
Indicates that one entity serves as a characteristic, aspect, or attribute highlighted in the depiction or representation of another entity.
-
B.
featuresCameoBy
Indicates that a work includes a brief, often special-appearance role performed by the specified person or entity.
-
C.
featuresReturnOf
Indicates that something (such as a work, event, or product) includes or highlights the comeback or reappearance of a person, character, element, or feature.
-
D.
featuresSample
Indicates that an entity includes or presents a particular sample as one of its components or examples.
-
E.
featuresText
Indicates that an entity includes or presents a specific piece of text as one of its characteristics or contents.
- 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_69c0082d6fe48190b777fb383769e5c8 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02459cd18819080fda0b481d11f08 |
completed | March 22, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69c021c2d8bc8190b947c7d1f423d2f3 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:45 p.m.