Triple
T8992925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khotanese language |
E214832
|
entity |
| Predicate | primarySourcesFoundIn |
P66558
|
FINISHED |
| Object | manuscripts |
—
|
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: manuscripts | Statement: [Khotanese language, primarySourcesFoundIn, manuscripts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primarySourcesFoundIn Context triple: [Khotanese language, primarySourcesFoundIn, manuscripts]
-
A.
primarySources
Indicates that one entity serves as an original, authoritative source of information or evidence for another entity.
-
B.
commonSources
Indicates that two or more entities share the same origin, cause, or source.
-
C.
primarySourceChapters
Indicates that specific chapters are identified as the primary source material for the referenced content or work.
-
D.
survivingSources
chosen
Indicates that there exist remaining or extant sources (e.g., documents, records, artifacts) that attest to or provide evidence about the subject.
-
E.
laterSources
Indicates that the information, claim, or reference is derived from sources that were created or recorded at a later time than the event or material being discussed.
- 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_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6876583081909d936dc3c3152587 |
completed | April 1, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:04 p.m.