Triple
T14904028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navsari |
E360080
|
entity |
| Predicate | officialLanguage |
P236
|
FINISHED |
| Object | Gujarati |
E8599
|
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: Gujarati | Statement: [Navsari, officialLanguage, Gujarati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gujarati Context triple: [Navsari, officialLanguage, Gujarati]
-
A.
Gujarati
chosen
Gujarati is an Indo-Aryan language primarily spoken in the Indian state of Gujarat and by Gujarati communities worldwide.
-
B.
Parsi Gujarati
Parsi Gujarati refers to members of the Zoroastrian Parsi community who are culturally and linguistically rooted in the Gujarati-speaking region of western India.
-
C.
Hindi
Hindi is an Indo-Aryan language widely spoken across northern and central India and used in government, education, media, and popular culture.
-
D.
Gojri
Gojri is an Indo-Aryan language traditionally spoken by the Gujjar community across parts of northern India and Pakistan.
-
E.
Sindhi
Sindhi is an Indo-Aryan language spoken primarily in Pakistan and India, known for its rich literary tradition and distinct script variants.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded60b24008190bd272c0d61329400 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72b4e4f88190af7e859d93dbbd28 |
completed | May 8, 2026, 11:33 p.m. |
Created at: April 10, 2026, 2:12 a.m.