Triple
T28996719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maclaurin buildings |
E736184
|
entity |
| Predicate | hasColonnadeAlong |
P18962
|
FINISHED |
| Object | Killian Court side |
—
|
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: Killian Court side | Statement: [Maclaurin buildings, hasColonnadeAlong, Killian Court side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColonnadeAlong Context triple: [Maclaurin buildings, hasColonnadeAlong, Killian Court side]
-
A.
hasColonnade
chosen
Indicates that one entity features or is characterized by a colonnade in relation to another entity.
-
B.
hasColonnadeShape
Indicates that something has the form or configuration characteristic of a colonnade, typically a sequence or arrangement of regularly spaced columns.
-
C.
numberOfColonnades
Indicates the quantity of colonnades associated with a given entity or structure.
-
D.
hasColonnadeMaterial
Indicates that a colonnade is made from, or primarily constructed using, a specified material.
-
E.
numberOfColumnsInColonnade
Indicates the count of individual columns that make up a given colonnade.
- 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a0017dd31d08190aa5e9f72df83733a |
completed | May 10, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_6a0015a1deb88190b9cdaa60455b0a33 |
completed | May 10, 2026, 5:20 a.m. |
Created at: April 28, 2026, 9:31 a.m.