Triple
T38634139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nahapana |
E937533
|
entity |
| Predicate | issuedGrants |
P131906
|
FINISHED |
| Object | land grants to religious institutions |
—
|
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: land grants to religious institutions | Statement: [Nahapana, issuedGrants, land grants to religious institutions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: issuedGrants Context triple: [Nahapana, issuedGrants, land grants to religious institutions]
-
A.
grantsAre
chosen
Indicates that one entity provides or awards grants to another entity.
-
B.
issuedWith
Indicates that one entity is formally provided, granted, or supplied together with another entity as part of the same issuance event.
-
C.
issuedAct
Indicates that an authority formally created, enacted, or put into effect a specific act, order, or legal instrument.
-
D.
numberOfGrants
Indicates the total count of grants associated with a given entity or context.
-
E.
aimedToGrant
Indicates an intention or effort to provide or confer something (such as a right, benefit, or permission) to a recipient.
- 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 3, 2026, 4:32 p.m.