Triple
T18400095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pushkar Lake |
E449968
|
entity |
| Predicate | hasGhat |
P13904
|
FINISHED |
| Object | Rangji Ghat |
—
|
NE NERFINISHED |
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: Rangji Ghat | Statement: [Pushkar Lake, hasGhat, Rangji Ghat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rangji Ghat Context triple: [Pushkar Lake, hasGhat, Rangji Ghat]
-
A.
Assi Ghat
Assi Ghat is a prominent riverfront step area in Varanasi, India, known as a major spiritual, cultural, and tourist hub on the banks of the Ganges.
-
B.
Fanase Ghat
Fanase Ghat is a riverside bathing and worship area located in the historic temple town of Maheshwar on the banks of the Narmada River in Madhya Pradesh, India.
-
C.
Brahma Ghat
chosen
Brahma Ghat is a sacred bathing and ritual site on the holy lake in Pushkar, Rajasthan, closely associated with worship of the Hindu god Brahma.
-
D.
Sojan Badiyar Ghat
Sojan Badiyar Ghat is a celebrated Bengali narrative poem by Jasimuddin that portrays rural life and a poignant love story set along a riverside village.
-
E.
Keshi Ghat
Keshi Ghat is a historic riverside bathing ghat in Vrindavan on the banks of the Yamuna, revered in Hindu tradition for its association with Lord Krishna.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e5194f2a8c8190afcd7db23e3795fb |
completed | April 19, 2026, 6:05 p.m. |
Created at: April 10, 2026, 10:46 a.m.