Triple
T16138294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jurchen |
E391586
|
entity |
| Predicate | scriptDerivedFrom |
P1245
|
FINISHED |
| Object | Khitan script |
E1101240
|
NE 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: Khitan script | Statement: [Jurchen, scriptDerivedFrom, Khitan script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khitan script Context triple: [Jurchen, scriptDerivedFrom, Khitan script]
-
A.
Khitan script
chosen
The Khitan script was an ancient writing system used by the Khitan people of northern China and Central Asia, notable for its complex logographic and syllabic forms and its role in recording the languages of the Liao and Qara Khitai empires.
-
B.
Chagatai script
The Chagatai script is a historical Perso-Arabic–based writing system used for the Chagatai Turkic literary language, which influenced later Central Asian Turkic languages including Uyghur.
-
C.
Sibe script
The Sibe script is an alphabetic writing system derived from the Manchu script, used primarily to write the Sibe language spoken by the Sibe people in China.
-
D.
Khojki script
The Khojki script is a historical writing system used primarily by the Nizari Ismaili community of South Asia to record religious and literary texts in languages such as Sindhi and Gujarati.
-
E.
Old Turkic script
The Old Turkic script is an ancient runiform alphabet used by early Turkic peoples to write the earliest known Turkic inscriptions across Central Asia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21a05e68881908319454a478cdda5 |
completed | April 17, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fffef0f51c8190bc039150af8ebf98 |
completed | May 10, 2026, 3:43 a.m. |
Created at: April 10, 2026, 5:01 a.m.