Triple
T19731024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sairandhri |
E473852
|
entity |
| Predicate | claimsHusband |
P115011
|
FINISHED |
| Object | Gandharva husband |
—
|
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: Gandharva husband | Statement: [Sairandhri, claimsHusband, Gandharva husband]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimsHusband Context triple: [Sairandhri, claimsHusband, Gandharva husband]
-
A.
throughMarriageClaim
Indicates that one entity asserts a right, status, or connection to another entity by virtue of a marital relationship rather than by direct or original entitlement.
-
B.
spouseClaimStatus
chosen
Indicates whether and how one person asserts or is recognized as being the spouse of another, such as claimed, unclaimed, or disputed marital status.
-
C.
claimedFather
Indicates that one entity is asserted or alleged to be the father of another entity, without guaranteeing the claim’s truth.
-
D.
claim1
Indicates that an entity asserts, alleges, or maintains the truth of a particular statement, proposition, or fact.
-
E.
claimsToBe
Indicates that one entity asserts or declares itself to have a particular identity, role, or property, regardless of whether this assertion is true.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649fd18148190a6e85b2be0069dde |
completed | April 20, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69e5304a7aac8190ac13f75f0c008e45 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:47 p.m.