Triple
T38046280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karmapa |
E949625
|
entity |
| Predicate | traditionalResidenceLocation |
P14194
|
FINISHED |
| Object | Tolung Valley, Tibet |
—
|
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: Tolung Valley, Tibet | Statement: [Karmapa, traditionalResidenceLocation, Tolung Valley, Tibet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalResidenceLocation Context triple: [Karmapa, traditionalResidenceLocation, Tolung Valley, Tibet]
-
A.
sharedResidenceLocation
Indicates that two or more entities live or have lived at the same residential location.
-
B.
namedAfterResidenceOf
Indicates that one entity is named after the place where another entity lives or has lived.
-
C.
traditionalRegionOfResidence
chosen
Indicates the customary or historically established geographic region where an entity (typically a person or group) resides or is considered to be from.
-
D.
residenceBasedOn
Indicates that an entity’s place of residence is determined or assigned based on a specified criterion, condition, or underlying factor.
-
E.
residencyAt
Indicates that an entity lives or has an established residence at a particular location or address.
- 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_69f76f000cf081908c11fb5443b392e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ffe8ebe9fc8190b1934a3c4074370c |
completed | May 10, 2026, 2:09 a.m. |
| PD | Predicate disambiguation | batch_69ffe83a5de88190bed3e8bac86e8760 |
completed | May 10, 2026, 2:06 a.m. |
Created at: May 3, 2026, 4:20 p.m.