Triple
T28127457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drepung Monastery |
E710967
|
entity |
| Predicate | monasticColleges |
P164061
|
FINISHED |
| Object | Loseling College |
—
|
NE NERFINISHED |
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: Loseling College | Statement: [Drepung Monastery, monasticColleges, Loseling College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monasticColleges Context triple: [Drepung Monastery, monasticColleges, Loseling College]
-
A.
monasticCenters
Indicates that one entity serves as a monastic center or hub for religious monastic life in relation to another entity.
-
B.
monasticCurriculum
Indicates that one entity is the structured course of study, training, or educational program followed within a monastic or religious community by another entity.
-
C.
monasteriesAre
Indicates that a subject is classified as, functions as, or is identified with monasteries.
-
D.
monasteryOrder
Indicates that a monastery belongs to, follows, or is affiliated with a particular religious order.
-
E.
monasticResidence
Indicates that one entity serves as the place of residence for a monastic individual or community.
- F. None of above. chosen
Provenance (4 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_69ef9b73bd288190a21ae3d6aa14f386 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6416fbf4081909b0913c337927fc4 |
completed | May 2, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
| PDg | Predicate description generation | batch_69f63fd4f7448190930c723ba7cfce62 |
completed | May 2, 2026, 6:17 p.m. |
Created at: April 27, 2026, 9:21 p.m.