Triple
T3257706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Monastery of San Juan de los Reyes |
E68335
|
entity |
| Predicate | hasCloisterLevel |
P17704
|
FINISHED |
| Object | two-storey cloister |
—
|
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: two-storey cloister | Statement: [Monastery of San Juan de los Reyes, hasCloisterLevel, two-storey cloister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCloisterLevel Context triple: [Monastery of San Juan de los Reyes, hasCloisterLevel, two-storey cloister]
-
A.
hasCloister
chosen
Indicates that one entity possesses or includes a cloister as part of its structure or layout.
-
B.
hasConcourseLevel
Indicates that an entity possesses or is associated with a specific concourse level within a building or facility.
-
C.
hasClanSeat
Indicates that an entity holds an official seat or position within a particular clan.
-
D.
hasLevel
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
-
E.
hasClanStatus
Indicates that an entity holds a specific role, rank, or membership status within a clan or clan-like group.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf6a46448190a7fa0ca83fa096f8 |
completed | March 8, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.