Triple
T29747906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kallazhagar |
E752808
|
entity |
| Predicate | primaryCelebrationLocation |
P128
|
FINISHED |
| Object | Madurai |
—
|
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: Madurai | Statement: [Kallazhagar, primaryCelebrationLocation, Madurai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryCelebrationLocation Context triple: [Kallazhagar, primaryCelebrationLocation, Madurai]
-
A.
ceremonyLocationType
Indicates the type or category of location where a ceremony takes place.
-
B.
publicCelebration
Indicates a relationship where an event, achievement, or occasion is celebrated openly and collectively in a public setting.
-
C.
capitalOfCelebration
Indicates that a location is recognized as the primary or central place where a particular celebration or festivity is most prominently held or symbolically based.
-
D.
celebrationAssociatedWith
Indicates a relationship where a celebration is connected to, linked with, or held in relation to a particular entity, event, or context.
-
E.
ceremonyLocation
chosen
Indicates the place where a ceremony is held or takes place.
- 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_69f0d62b064081908c1ae61cd68fb139 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a01839b071481909f9cc79a6a09387d |
completed | May 11, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_6a017edbed688190baa61cbae5110c8e |
completed | May 11, 2026, 7:01 a.m. |
Created at: April 28, 2026, 7:52 p.m.