Triple
T31611676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akula-class submarine |
E806642
|
entity |
| Predicate | leasedUnitNameInIndia |
P128067
|
FINISHED |
| Object | INS Chakra |
—
|
NE NERFINISHED |
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: INS Chakra | Statement: [Akula-class submarine, leasedUnitNameInIndia, INS Chakra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leasedUnitNameInIndia Context triple: [Akula-class submarine, leasedUnitNameInIndia, INS Chakra]
-
A.
downstreamNameInIndia
chosen
Indicates that the referenced entity is known by this specific name in the downstream (later-stage or consumer-facing) context within India.
-
B.
releaseDateIndia
Indicates the date on which something (such as a product, film, or publication) is officially released or made available in India.
-
C.
partlyLocatedInIndianState
Indicates that an entity is geographically or administratively situated such that only part of it lies within the boundaries of a specified Indian state.
-
D.
manufacturerInIndia
Indicates that a manufacturer is located in or operates within India.
-
E.
leasedFrom
Indicates that one entity is renting or leasing something from another entity, which acts as the owner or lessor.
- 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_69f348d61f2081908cad94bc9ffbb671 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a873ff8c819086fba9ef9a1e3c58 |
completed | May 3, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:37 p.m.