Triple
T38489067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaya |
E918002
|
entity |
| Predicate | hasMarkets |
P2714
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Kaya, hasMarkets, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarkets Context triple: [Kaya, hasMarkets, yes]
-
A.
hasMarket
chosen
Indicates that an entity possesses, operates in, or is associated with a particular market or marketplace.
-
B.
hasRetailMarkets
Indicates that an entity operates, hosts, or is associated with one or more retail markets where goods or services are sold to consumers.
-
C.
hasMarketStatus
Indicates the current commercial or trading condition of an entity, such as whether it is active, suspended, listed, or delisted in a market.
-
D.
hasMarketBeyond
Indicates that something is sold, demanded, or has commercial presence in regions or markets outside its primary or original one.
-
E.
hasIntermediateMarket
Indicates that there exists a secondary or intermediary market through which the subject’s goods, services, or assets are traded or distributed before reaching the final market.
- 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_69f76e9894208190a129a553a60ca58c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:31 p.m.