Triple
T17087309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crosby Beach |
E414631
|
entity |
| Predicate | sculptureSubject |
P23770
|
FINISHED |
| Object | life-size human figures |
—
|
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: life-size human figures | Statement: [Crosby Beach, sculptureSubject, life-size human figures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sculptureSubject Context triple: [Crosby Beach, sculptureSubject, life-size human figures]
-
A.
featuresSculptureOf
chosen
Indicates that one entity includes or displays a sculpture that depicts or represents another entity.
-
B.
notableSculpture
Indicates that an entity is a sculpture for which the subject is especially known or recognized.
-
C.
artStyleOfEnclosingSculpture
Indicates that one entity specifies the artistic style or aesthetic category of a surrounding or enclosing sculpture associated with another entity.
-
D.
usesSculptureFor
Indicates that one entity employs or utilizes a sculpture for a particular purpose, function, or activity.
-
E.
completionOfSculptures
Indicates that one entity is responsible for finishing or bringing to completion the creation or production of sculptures associated with another entity.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe7ccb48190b8fb39e2a0ba0782 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d67b14481909fcdbdeaa5c34785 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:35 a.m.