Triple
T26029317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNIA |
E647383
|
entity |
| Predicate | heldConventionIn |
P24931
|
FINISHED |
| Object | New York City |
—
|
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: New York City | Statement: [UNIA, heldConventionIn, New York City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldConventionIn Context triple: [UNIA, heldConventionIn, New York City]
-
A.
areHeldIn
Indicates that events, activities, or objects take place or are located within a particular venue, container, or setting.
-
B.
associatedConvention
Indicates a relationship where something is linked or connected to a particular convention (such as an event, standard, or formal gathering).
-
C.
oftenHeldAs
Indicates that one entity is frequently regarded, considered, or believed to be in a particular way with respect to another entity or property.
-
D.
convenedIn
chosen
Indicates that an event, meeting, or formal gathering was brought together and held at a specific location.
-
E.
heldEvery
Indicates that an entity consistently possessed or maintained control of another entity throughout every instance or period within a specified range.
- 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_69e77e8b60e88190a3b26c4f0032a2c2 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605ee5ba88190bc99652ac24b69b0 |
completed | May 2, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 9:05 a.m.