Triple
T19707761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tulabharam ritual |
E473258
|
entity |
| Predicate | offeringRecipient |
P12761
|
FINISHED |
| Object | temple |
—
|
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: temple | Statement: [Tulabharam ritual, offeringRecipient, temple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offeringRecipient Context triple: [Tulabharam ritual, offeringRecipient, temple]
-
A.
recipientOf
Indicates that one entity is the receiver or beneficiary of something (such as an item, message, or action) from another entity.
-
B.
individualRecipient
Indicates that a specific individual is the direct recipient or beneficiary of something (such as an item, message, or action).
-
C.
grantRecipient
Indicates that one entity is the recipient or beneficiary of a grant provided by another entity.
-
D.
uniqueRecipient
Indicates that an action or item is directed to exactly one distinct recipient, with no other recipients involved.
-
E.
organizationRecipient
chosen
Indicates that an organization is the recipient or beneficiary of something provided, sent, or directed 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642bc754481908bdf5bfad069aec8 |
completed | April 20, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:46 p.m.