Triple
T11589072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | S&P BSE 500 |
E274830
|
entity |
| Predicate | typeOfConstituents |
P14960
|
FINISHED |
| Object | listed companies on BSE |
—
|
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: listed companies on BSE | Statement: [S&P BSE 500, typeOfConstituents, listed companies on BSE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfConstituents Context triple: [S&P BSE 500, typeOfConstituents, listed companies on BSE]
-
A.
numberOfConstituentsType
Indicates the type or category used to classify how many constituents (parts or members) are involved in or associated with something.
-
B.
numberOfConstituents
Indicates the total count of individual components or members that make up a larger whole or group.
-
C.
typicalConstituentType
Indicates the usual or characteristic type of component that typically makes up or forms part of something.
-
D.
majorConstituentType
Indicates the type or category of a primary or dominant component that makes up a larger whole.
-
E.
constitutedBy
chosen
Indicates that something is made up of, composed from, or formed by the specified parts or elements.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d89463360c8190b91228c46bfe2e5f |
completed | April 10, 2026, 6:10 a.m. |
| PD | Predicate disambiguation | batch_69d85dcbacd0819094d4a1237055affa |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:38 p.m.