Triple
T6880558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Court, Selwyn College, Cambridge |
E158781
|
entity |
| Predicate | typicalFeatureOf |
P5084
|
FINISHED |
| Object | Cambridge college architecture |
—
|
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: Cambridge college architecture | Statement: [Old Court, Selwyn College, Cambridge, typicalFeatureOf, Cambridge college architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalFeatureOf Context triple: [Old Court, Selwyn College, Cambridge, typicalFeatureOf, Cambridge college architecture]
-
A.
typicalFeatures
chosen
Indicates that the related entities are characteristic or commonly occurring features or attributes of something.
-
B.
notableFeatureOn
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
C.
iconicFeature
Indicates that something serves as a distinctive, widely recognized characteristic or symbol of another entity.
-
D.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
E.
dominatingFeature
Indicates that one feature stands out as the most prominent or influential characteristic in relation to others.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8e798c08190b1f494a2c1445514 |
completed | March 27, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b53e9881909ec298daa9f1913b |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:23 p.m.