Triple
T19983490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Feature Competition |
E493875
|
entity |
| Predicate | parentEventType |
P18954
|
FINISHED |
| Object | annual film festival |
—
|
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: annual film festival | Statement: [First Feature Competition, parentEventType, annual film festival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parentEventType Context triple: [First Feature Competition, parentEventType, annual film festival]
-
A.
parentEvent
chosen
Indicates that one event serves as the higher-level or originating event from which another event is derived, contained, or logically dependent.
-
B.
associatedEventType
Indicates that one entity is linked to another by the type or category of event with which it is associated.
-
C.
parentType
Indicates that one entity serves as the direct parent or higher-level type from which another entity is derived or classified.
-
D.
componentEventType
Indicates the type or category of event associated with a specific component.
-
E.
appearsAtEventType
Indicates that an entity is present or participates in an event of a specified type.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d14c3c08190b1ba8f4da08a4ccf |
completed | April 20, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69e537fae79c81909eae39500766d0b6 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:28 p.m.