Triple
T859696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Om |
E18571
|
entity |
| Predicate | script |
P505
|
FINISHED |
| Object | Gurmukhi script |
E12238
|
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: Gurmukhi script | Statement: [Om, script, Gurmukhi script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gurmukhi script Context triple: [Om, script, Gurmukhi script]
-
A.
Gurmukhi
chosen
Gurmukhi is an Indic writing system primarily used for the Punjabi language and for recording Sikh religious scriptures.
-
B.
Shahmukhi script
Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
-
C.
Devanagari script
Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
-
D.
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.
-
E.
Eastern Nagari script
The Eastern Nagari script is an abugida used across eastern South Asia, most prominently for writing the Bengali and Assamese languages.
- 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_69a4938bdd3c8190a954a3c11844d9cf |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac50e5ec81908ac0c4b7123b4ebb |
completed | March 1, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7a3c3d2fc8190b9f76d31528feeb6 |
completed | March 4, 2026, 3:15 a.m. |
Created at: March 1, 2026, 7:39 p.m.