Triple
T29298514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pandya king of Madurai |
E742897
|
entity |
| Predicate | primaryLocationInText |
P136244
|
FINISHED |
| Object | city of Madurai |
—
|
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: city of Madurai | Statement: [Pandya king of Madurai, primaryLocationInText, city of Madurai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryLocationInText Context triple: [Pandya king of Madurai, primaryLocationInText, city of Madurai]
-
A.
primaryLocationCity
chosen
Indicates the city that serves as the main or primary location associated with the subject.
-
B.
primaryPostingLocation
Indicates the main or default location where an entity (such as a message, job, or content item) is originally posted or primarily published.
-
C.
mainLocation
Indicates that one entity serves as the primary or central location associated with another entity.
-
D.
homeLocationInStory
Indicates the place that serves as a character’s primary home or base of residence within the context of the story.
-
E.
coreLocation
Indicates that one entity serves as the central or primary location associated with another entity.
- 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_69f0912323c48190b9a24ef8cf359225 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a00d820a7788190a8d54625cd87be68 |
completed | May 10, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_6a00d7c5b40c8190b80413238d04e81e |
completed | May 10, 2026, 7:08 p.m. |
Created at: April 28, 2026, 1:08 p.m.