Triple
T4782784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurma |
E106404
|
entity |
| Predicate | avatarOrder |
P37518
|
FINISHED |
| Object | second avatar of Vishnu |
—
|
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: second avatar of Vishnu | Statement: [Kurma, avatarOrder, second avatar of Vishnu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: avatarOrder Context triple: [Kurma, avatarOrder, second avatar of Vishnu]
-
A.
displayOrder
Indicates the sequence or position in which items should be presented or shown relative to one another.
-
B.
orderOf
chosen
Indicates that one entity is arranged, ranked, or sequenced before or after another according to a specified ordering criterion.
-
C.
wearingOrder
Indicates the relative sequence in which items are worn on or over one another (e.g., which garment is worn over or under another).
-
D.
orderedBy
Indicates that one entity has placed a request or purchase for another entity, typically specifying who initiated the order.
-
E.
ordersBy
Indicates that one entity arranges, sorts, or sequences another entity according to a specified criterion or set of criteria.
- 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_69bd43f4a9588190bf73e20bc27c03cc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd69237f80819090713ed62653fb75 |
completed | March 20, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69bd622be1388190ab5511b589c878c0 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:22 p.m.