Triple
T5459775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashokan inscriptions |
E122567
|
entity |
| Predicate | script |
P505
|
FINISHED |
| Object | Kharosthi script |
E125350
|
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: Kharosthi script | Statement: [Ashokan inscriptions, script, Kharosthi script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kharosthi script Context triple: [Ashokan inscriptions, script, Kharosthi script]
-
A.
Kharoṣṭhī script
chosen
The Kharoṣṭhī script is an ancient right-to-left writing system used in northwestern South Asia, especially in the Gandhāra region, primarily for early Buddhist and administrative texts.
-
B.
Shahmukhi script
Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
-
C.
Brahmi script
The Brahmi script is one of the oldest writing systems of the Indian subcontinent, serving as the ancestor of most modern South and Southeast Asian scripts.
-
D.
Tirhuta script
Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
-
E.
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.
- 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_69bd46424248819085282ddf50a565f3 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd91f353c481909ae1a73ae419fb9a |
completed | March 20, 2026, 6:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf6c6c2454819096da8367f6b94233 |
completed | March 22, 2026, 4:13 a.m. |
Created at: March 20, 2026, 2:08 p.m.