Triple
T28996676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Building 10 |
E736183
|
entity |
| Predicate | hasCourtyardRelation |
P88908
|
FINISHED |
| Object | forms northern edge of Killian Court |
—
|
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: forms northern edge of Killian Court | Statement: [Building 10, hasCourtyardRelation, forms northern edge of Killian Court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCourtyardRelation Context triple: [Building 10, hasCourtyardRelation, forms northern edge of Killian Court]
-
A.
hasCourtyard
Indicates that one entity includes, features, or is characterized by the presence of a courtyard.
-
B.
hasCourtyardFeature
Indicates that a courtyard possesses or includes a specific feature or characteristic.
-
C.
courtyardRelation
chosen
Indicates a spatial relationship where one entity serves as, is located in, or is directly associated with the courtyard area of another entity.
-
D.
hasCourtyardArea
Indicates that an entity includes or is associated with a courtyard and specifies the size or extent of that courtyard space.
-
E.
hasCourtyardUse
Indicates that one entity is permitted or designated to use the courtyard of 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a001540d4f881908a4688881875e774 |
completed | May 10, 2026, 5:18 a.m. |
| PD | Predicate disambiguation | batch_6a0014a8cdd88190a67a90a2df2c5e18 |
completed | May 10, 2026, 5:16 a.m. |
Created at: April 28, 2026, 9:31 a.m.