Triple
T791388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agra |
E16921
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Mathura |
E26469
|
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: Mathura | Statement: [Agra, nearbyCity, Mathura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mathura Context triple: [Agra, nearbyCity, Mathura]
-
A.
Mathura
chosen
Mathura is an ancient city in northern India revered in Hinduism as the birthplace of Lord Krishna and a major pilgrimage center.
-
B.
Ayodhya
Ayodhya is an ancient city in India revered in Hinduism as the birthplace of Lord Rama and a major pilgrimage site.
-
C.
Dahanapura
Dahanapura was the principal city and political center of the historical Kediri Kingdom in Java.
-
D.
Gangaur
Gangaur is a prominent Rajasthani festival dedicated to the worship of Goddess Gauri, celebrating marital fidelity, prosperity, and the well-being of women.
-
E.
Vrindavan
Vrindavan is a major Hindu pilgrimage town in Uttar Pradesh, India, revered as a principal center of devotion to Lord Krishna and associated with many temples, sacred groves, and legends from his life.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a798c7608190b9c79c52a1fe0859 |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a826cc938481909e420185871a5d27 |
completed | March 4, 2026, 12:34 p.m. |
Created at: March 1, 2026, 7:38 p.m.