Triple
T38170890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gandhak Ki Baoli |
E1000070
|
entity |
| Predicate | waterBelief |
P188095
|
FINISHED |
| Object | water believed to have medicinal properties |
—
|
LITERAL 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: water believed to have medicinal properties | Statement: [Gandhak Ki Baoli, waterBelief, water believed to have medicinal properties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterBelief Context triple: [Gandhak Ki Baoli, waterBelief, water believed to have medicinal properties]
-
A.
waterIsBelievedTo
chosen
Indicates that someone holds a belief or assumption about water, such as its properties, behavior, or effects.
-
B.
waterSymbolizes
Indicates that water is used as a symbol or metaphor representing a particular idea, quality, or concept.
-
C.
sacredWaterBody
Indicates that a water body holds religious or spiritual significance within a belief system or ritual practice.
-
D.
waterIsKnownFor
Indicates that something is recognized or notable for its association with water, such as its abundance, use, or characteristic relation to water.
-
E.
domainOfBelief
Indicates the conceptual area or subject matter that a particular belief pertains to or is about.
- F. None of above.
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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fe7b1c506c8190869c1a22031e0571 |
completed | May 9, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69fe796b2bdc8190a86980d44008f875 |
completed | May 9, 2026, 12:01 a.m. |
Created at: May 3, 2026, 4:29 p.m.