Triple
T4931244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troyan Monastery |
E110698
|
entity |
| Predicate | hasCloisterPlan |
P17704
|
FINISHED |
| Object | closed rectangular courtyard |
—
|
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: closed rectangular courtyard | Statement: [Troyan Monastery, hasCloisterPlan, closed rectangular courtyard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCloisterPlan Context triple: [Troyan Monastery, hasCloisterPlan, closed rectangular courtyard]
-
A.
hasCloister
chosen
Indicates that one entity possesses or includes a cloister as part of its structure or layout.
-
B.
hasStreetPlan
Indicates that an entity possesses or is associated with a specific layout or design plan for its streets.
-
C.
hasPlanningConcept
Indicates that an entity is associated with, defined by, or governed by a particular planning-related concept or framework.
-
D.
hasPlannedCity
Indicates that an entity has a city that was deliberately designed and constructed according to a prearranged plan.
-
E.
hasPlan
Indicates that an entity possesses or is associated with a specific plan or course of action.
- 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_69bd4415190c8190817bee7ec9f9f944 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd706245e48190a61d573438461c30 |
completed | March 20, 2026, 4:05 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3695c8819094e7ad2f6d4ba1ac |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:30 p.m.