Triple
T22582230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teatro Sant’Angelo |
E544594
|
entity |
| Predicate | locatedInWaterCity |
P135498
|
FINISHED |
| Object | Venice lagoon |
—
|
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: Venice lagoon | Statement: [Teatro Sant’Angelo, locatedInWaterCity, Venice lagoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInWaterCity Context triple: [Teatro Sant’Angelo, locatedInWaterCity, Venice lagoon]
-
A.
isCentralWaterfrontOf
Indicates that one location serves as the primary waterfront area or main waterside district of another place.
-
B.
locatedInWaterfrontArea
Indicates that something is situated within a designated waterfront area adjacent to a body of water.
-
C.
locatedInWaterfrontTown
chosen
Indicates that the subject is situated within a town that is directly adjacent to or closely associated with a body of water, such as a sea, lake, or river.
-
D.
locatedInWaterBodyType
Indicates that an entity is situated within or on a body of water of a specified type (e.g., lake, river, ocean).
-
E.
locatedOnWaterbody
Indicates that an entity is situated on or directly adjacent to a specified body of water.
- 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_69e11e30d05481909df915354c89f0d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f15ff13e288190b5e4b527470be75e |
completed | April 29, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69ee626e6bb08190ada4dd8b48cc0c43 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 16, 2026, 8:53 p.m.