Triple
T34167684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wind organ on the boulevard |
E876455
|
entity |
| Predicate | audibleFrom |
P45475
|
FINISHED |
| Object | Vlissingen boulevard |
—
|
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: Vlissingen boulevard | Statement: [Wind organ on the boulevard, audibleFrom, Vlissingen boulevard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: audibleFrom Context triple: [Wind organ on the boulevard, audibleFrom, Vlissingen boulevard]
-
A.
audibleIn
chosen
Indicates that a sound produced by one entity can be heard within the spatial or contextual range of another entity.
-
B.
hasAudiobookVersion
Indicates that an entity has a corresponding version available in audiobook format.
-
C.
narratedFrom
Indicates that an event, story, or account is told or described from the perspective or vantage point of a particular source or narrator.
-
D.
usesAudioFrom
Indicates that one entity incorporates or relies on the audio content produced or provided by another entity.
-
E.
narratedTo
Indicates that one entity tells or recounts a story, event, or information directly to another entity as the audience.
- 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_69f349ad97ac8190bf1f17417c970e64 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70fe0aa4881908023119b94d9fcbe |
completed | May 3, 2026, 9:05 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:54 a.m.