Triple
T10115801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Wharf |
E218353
|
entity |
| Predicate | publicSpaceFeature |
P31591
|
FINISHED |
| Object | waterfront promenade |
—
|
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: waterfront promenade | Statement: [The Wharf, publicSpaceFeature, waterfront promenade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicSpaceFeature Context triple: [The Wharf, publicSpaceFeature, waterfront promenade]
-
A.
spaceType
Indicates the category or kind of physical or conceptual space associated with an entity.
-
B.
openSpaceType
Indicates the type or category of an open space associated with an entity (e.g., park, plaza, courtyard).
-
C.
hasPublicSpaceAlong
chosen
Indicates that a public space (such as a park, plaza, or walkway) is located adjacent to or runs alongside the referenced feature or element.
-
D.
administrativeFeature
Indicates that one entity serves as an administrative or governance-related feature, function, or attribute associated with another entity.
-
E.
performanceSpaceType
Indicates the specific kind or category of space in which a performance or event takes place.
- 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_69ca83da93fc8190b54e44bc2b34857c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd161831c81908bb3c77caa7c3ce1 |
completed | April 2, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.