Triple
T37699225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | trading members of Pakistan Stock Exchange |
E939011
|
entity |
| Predicate | operatesOnMarket |
P2714
|
FINISHED |
| Object | Pakistan Stock Exchange |
E56693
|
NE 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: Pakistan Stock Exchange | Statement: [trading members of Pakistan Stock Exchange, operatesOnMarket, Pakistan Stock Exchange]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesOnMarket Context triple: [trading members of Pakistan Stock Exchange, operatesOnMarket, Pakistan Stock Exchange]
-
A.
governsMarket
Indicates that one entity exercises regulatory or controlling authority over the functioning, rules, or behavior of a particular market.
-
B.
hasMarket
chosen
Indicates that an entity possesses, operates in, or is associated with a particular market or marketplace.
-
C.
exportMarket
Indicates that an entity serves as a destination market to which another entity exports goods or services.
-
D.
marketOperatedBy
Indicates that a market is managed, controlled, or run by a specific operator or organization.
-
E.
marketType
Indicates the classification or category of market in which an entity operates or a transaction occurs (e.g., retail, wholesale, online).
- F. None of above.
Provenance (4 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_69f76eda6ae48190b3111071eeacc038 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0309a4e4d481908a6070b40d507aae |
completed | May 12, 2026, 11:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a412c9742e881908513ac0918f2eae8 |
completed | June 28, 2026, 2:15 p.m. |
| PD | Predicate disambiguation | batch_6a03091ac1008190bf50357364d4e9e4 |
completed | May 12, 2026, 11:03 a.m. |
Created at: May 3, 2026, 4:18 p.m.