Triple
T25587210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bank of Madras |
E641417
|
entity |
| Predicate | sisterBank |
P158317
|
FINISHED |
| Object | Bank of Bengal |
—
|
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: Bank of Bengal | Statement: [Bank of Madras, sisterBank, Bank of Bengal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sisterBank Context triple: [Bank of Madras, sisterBank, Bank of Bengal]
-
A.
sisterBank
chosen
Indicates a relationship where two banks are affiliated or related under common ownership or control, typically operating as counterparts within the same corporate group or network.
-
B.
servesBank
Indicates that one entity provides banking or financial services to another entity.
-
C.
tributaryBank
Indicates that one bank or financial institution is a subsidiary or dependent branch of another, larger or primary bank.
-
D.
riverBankOne
Indicates that the referenced entity is one specific side or bank of a river, typically the first or primary one in a pairwise relation.
-
E.
hasFinancialInstitution
Indicates that one entity is associated with or linked to a financial institution, such as a bank or similar financial service provider.
- 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_69e75dc42b588190a98b58e0df359674 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f96a44bc8190a38439dbc297ebc5 |
completed | May 2, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 4:17 p.m.