Triple
T30871969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marvel One-Shot: The Consultant |
E786364
|
entity |
| Predicate | archiveFootageOf |
P179517
|
FINISHED |
| Object | Robert Downey Jr. |
—
|
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: Robert Downey Jr. | Statement: [Marvel One-Shot: The Consultant, archiveFootageOf, Robert Downey Jr.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: archiveFootageOf Context triple: [Marvel One-Shot: The Consultant, archiveFootageOf, Robert Downey Jr.]
-
A.
usesArchivalFootageFrom
chosen
Indicates that one entity incorporates or includes archival footage originating from another entity.
-
B.
includesNewFootageWith
Indicates that one entity (such as a media release or edition) contains additional or previously unseen footage associated with another entity.
-
C.
associatedVideoImagery
Indicates a relationship where specific video imagery is linked or connected to another entity (such as an event, object, or record) as related visual content.
-
D.
originalFootageFilmedInYear
Indicates that the original footage associated with an entity was filmed in the specified year.
-
E.
usesFootageType
Indicates that one entity employs or incorporates a particular type or category of footage in its content or production.
- 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_69f224b9df2c819086f55f8bcf7f382e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
Created at: April 29, 2026, 8:48 p.m.