Triple
T34216001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Florida Flight 90 crash |
E877789
|
entity |
| Predicate | bridgeStruck |
P178538
|
FINISHED |
| Object | 14th Street Bridge |
—
|
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: 14th Street Bridge | Statement: [Air Florida Flight 90 crash, bridgeStruck, 14th Street Bridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bridgeStruck Context triple: [Air Florida Flight 90 crash, bridgeStruck, 14th Street Bridge]
-
A.
bridgeRebuilt
Indicates that a previously existing bridge has been reconstructed or restored after damage, destruction, or disuse.
-
B.
bridgeOpened
Indicates that a bridge has transitioned from a closed or inactive state to being open and available for use.
-
C.
bridgeCarries
Indicates that a bridge serves as a route or support structure for transporting or conveying something (such as vehicles, pedestrians, or utilities) across an obstacle.
-
D.
riverCrossingStructure
Indicates a structure that allows passage across a river, such as by spanning or traversing it.
-
E.
bridgeStructure
Indicates a structural relationship where one entity functions as a bridge that spans or connects two separate points or areas.
- 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_69f349b0b4bc819088c1552424089ee9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f710aaff588190adc6cc5b7d5424cc |
completed | May 3, 2026, 9:08 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
| PDg | Predicate description generation | batch_69f70fddd43c819088dee5a448c72cbe |
completed | May 3, 2026, 9:05 a.m. |
Created at: May 1, 2026, 1:55 a.m.