Triple
T1106376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumbh Mela |
E25496
|
entity |
| Predicate | heldAtRiver |
P165
|
FINISHED |
| Object |
Shipra
Shipra is a sacred river in the Indian state of Madhya Pradesh, especially revered in Ujjain as a major Hindu pilgrimage site.
|
E131390
|
NE FINISHED |
How this triple was built (4 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: Shipra | Statement: [Kumbh Mela, heldAtRiver, Shipra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shipra Context triple: [Kumbh Mela, heldAtRiver, Shipra]
-
A.
Shruti
Shruti is the body of divinely revealed Hindu sacred knowledge, encompassing the Vedas and considered the highest authoritative scripture in Hinduism.
-
B.
Vishakha
Vishakha is a celebrated Marathi poetry collection by Vishnu Vaman Shirwadkar (Kusumagraj), renowned for its lyrical depth and humanistic themes.
-
C.
Vandana
Vandana is the first name of Vandana Shiva, an Indian scholar, environmental activist, and advocate of ecofeminism and sustainable agriculture.
-
D.
Pranhita
Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
-
E.
Chitrangada
Chitrangada is a warrior princess from the Indian epic Mahabharata, known as one of Arjuna’s wives and the daughter of the king of Manipur.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Shipra Triple: [Kumbh Mela, heldAtRiver, Shipra]
Generated description
Shipra is a sacred river in the Indian state of Madhya Pradesh, especially revered in Ujjain as a major Hindu pilgrimage site.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Shipra Target entity description: Shipra is a sacred river in the Indian state of Madhya Pradesh, especially revered in Ujjain as a major Hindu pilgrimage site.
-
A.
Shruti
Shruti is the body of divinely revealed Hindu sacred knowledge, encompassing the Vedas and considered the highest authoritative scripture in Hinduism.
-
B.
Vishakha
Vishakha is a celebrated Marathi poetry collection by Vishnu Vaman Shirwadkar (Kusumagraj), renowned for its lyrical depth and humanistic themes.
-
C.
Vandana
Vandana is the first name of Vandana Shiva, an Indian scholar, environmental activist, and advocate of ecofeminism and sustainable agriculture.
-
D.
Pranhita
Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
-
E.
Chitrangada
Chitrangada is a warrior princess from the Indian epic Mahabharata, known as one of Arjuna’s wives and the daughter of the king of Manipur.
- F. None of above. chosen
Provenance (5 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bb75eec08190b1d6545e96816d34 |
completed | March 1, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac5ea8abe081908a6f38cb78638740 |
completed | March 7, 2026, 5:21 p.m. |
| NEDg | Description generation | batch_69ac5f248db081908596810839ee6160 |
completed | March 7, 2026, 5:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac5fb242488190bf99f63956aeda13 |
completed | March 7, 2026, 5:26 p.m. |
Created at: March 1, 2026, 7:43 p.m.