Triple
T37107482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Supporting Actress for Olympia Dukakis |
E918884
|
entity |
| Predicate | linkedToRoleType |
P20417
|
FINISHED |
| Object | supporting role |
—
|
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: supporting role | Statement: [Academy Award for Best Supporting Actress for Olympia Dukakis, linkedToRoleType, supporting role]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedToRoleType Context triple: [Academy Award for Best Supporting Actress for Olympia Dukakis, linkedToRoleType, supporting role]
-
A.
refersToRole
Indicates that one entity designates, mentions, or points to another entity specifically in its capacity as a role or position.
-
B.
linkRole
Indicates a role or function that an entity plays within a specific link or relationship between entities.
-
C.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
D.
linkType
chosen
Indicates the specific kind or category of relationship that connects two linked entities.
-
E.
connectsRole
Indicates a relationship in which one entity is linked to another by assigning or associating a specific role between them.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fed48d8e148190a99c0aea29f8a3ee |
completed | May 9, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fed3c82a24819095e614e31ac0307f |
completed | May 9, 2026, 6:27 a.m. |
Created at: May 3, 2026, 4:14 p.m.