Triple
T8807381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahatma Gandhi Institute of Medical Sciences |
E209566
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Sevagram |
E39954
|
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: Sevagram | Statement: [Mahatma Gandhi Institute of Medical Sciences, locatedIn, Sevagram]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sevagram Context triple: [Mahatma Gandhi Institute of Medical Sciences, locatedIn, Sevagram]
-
A.
Sevagram
chosen
Sevagram is a village in Maharashtra, India, best known as Mahatma Gandhi’s residence and the site of his Sevagram Ashram during the Indian independence movement.
-
B.
Haladhara
Haladhara is another name for the Hindu deity Balarama, revered as Krishna’s elder brother and famed for wielding the plough as his primary weapon.
-
C.
Shegaon
Shegaon is a town in Maharashtra, India, best known as a major pilgrimage center associated with the revered saint Gajanan Maharaj.
-
D.
Sawerigadi
Sawerigadi is a town in Indonesia located in the province of Southeast Sulawesi.
-
E.
Singhwara
Singhwara is a town located in the Darbhanga district of the Indian state of Bihar.
- 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_69ca836320e48190b5cf585b90a322c4 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5fd2fadc81908b27e9296885af2b |
completed | March 31, 2026, 11:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf8921a13081909346b97c024110b6 |
completed | April 3, 2026, 9:32 a.m. |
Created at: March 30, 2026, 6:45 p.m.