Triple
T25490607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pookalam |
E638826
|
entity |
| Predicate | isCreatedOn |
P1431
|
FINISHED |
| Object | courtyard |
—
|
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: courtyard | Statement: [Pookalam, isCreatedOn, courtyard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCreatedOn Context triple: [Pookalam, isCreatedOn, courtyard]
-
A.
createdIn
chosen
Indicates that one entity was brought into existence, produced, or originated within the context, location, or time frame specified by another entity.
-
B.
createdAs
Indicates that one entity was originally made, designed, or brought into existence in the form, role, or identity specified by another entity.
-
C.
createdWith
Indicates that something was produced, built, or brought into existence using a particular tool, method, material, or resource.
-
D.
createdTo
Indicates that one entity was brought into existence, produced, or designed specifically for the purpose, use, or function of another entity.
-
E.
createdFor
Indicates that one entity was made, produced, or designed specifically to serve, benefit, or be used by 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_69e75dbbd2a88190b70e1e645de14b9a |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f7a4658081908758aa293923090d |
completed | May 2, 2026, 1:09 p.m. |
| PD | Predicate disambiguation | batch_69f5afd5baac8190bb8ed576813c8591 |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 2:38 p.m.