Triple
T3905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John F. Kennedy International Airport |
E74
|
entity |
| Predicate | opened |
P421
|
FINISHED |
| Object | 1948 |
—
|
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: 1948 | Statement: [John F. Kennedy International Airport, opened, 1948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opened Context triple: [John F. Kennedy International Airport, opened, 1948]
-
A.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
B.
allows
Indicates that one entity grants permission, capability, or opportunity for another entity to perform an action or be in a certain state.
-
C.
submittedTo
Indicates that one entity has formally sent or presented something (such as a document, request, or work) to another entity for consideration, review, or processing.
-
D.
developed
Indicates that one entity created, designed, or brought another entity into a more advanced or complete state through effort or work.
-
E.
settled
Indicates that an entity established residence or a stable presence in a place, typically after moving from elsewhere.
- F. None of above. chosen
Provenance (4 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23bcc8eb48190b897cc331563980a |
completed | Feb. 28, 2026, 12:50 a.m. |
| PD | Predicate disambiguation | batch_69a23994309081909ff3e869deef2156 |
completed | Feb. 28, 2026, 12:40 a.m. |
| PDg | Predicate description generation | batch_69a23bcb4bbc819093775f623998d62d |
completed | Feb. 28, 2026, 12:50 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.