Triple
T209056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harkness Tower |
E4672
|
entity |
| Predicate | hasStyleFeature |
P182
|
FINISHED |
| Object | Gothic tracery |
—
|
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: Gothic tracery | Statement: [Harkness Tower, hasStyleFeature, Gothic tracery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStyleFeature Context triple: [Harkness Tower, hasStyleFeature, Gothic tracery]
-
A.
hasStyle
Indicates that an entity possesses, exhibits, or is characterized by a particular style or manner.
-
B.
hasFeature
chosen
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
C.
hasSubstyle
Indicates that one style is a more specific or subordinate variant of another style within a hierarchical style structure.
-
D.
supportsFeature
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
E.
hasHigherStyleThan
Indicates that one entity’s style is considered superior or more fashionable than another’s.
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25e8b9b908190b69a3f0594b95f7e |
completed | Feb. 28, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69a25b4e3c2881908d83e8218aa9f2d9 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:51 a.m.