Triple
T30444112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soai Kinh Lam fabric market |
E774528
|
entity |
| Predicate | typicalTransaction |
P40844
|
FINISHED |
| Object | bulk fabric purchase |
—
|
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: bulk fabric purchase | Statement: [Soai Kinh Lam fabric market, typicalTransaction, bulk fabric purchase]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalTransaction Context triple: [Soai Kinh Lam fabric market, typicalTransaction, bulk fabric purchase]
-
A.
transaction
Indicates a transfer of value or assets between parties, typically involving an exchange such as payment for goods or services.
-
B.
transactionNature
chosen
Indicates the type or character of a transaction, specifying what kind of exchange or operation is taking place between the involved parties.
-
C.
notableTransaction
Indicates that a transaction between entities is significant or noteworthy in context, such as being unusually large, important, or otherwise exceptional.
-
D.
transactionRole
Indicates the specific function or capacity an entity assumes within a transaction (such as buyer, seller, payer, or recipient).
-
E.
transactionModel
Indicates a relationship where an entity uses or is governed by a specific structured framework or schema for conducting, recording, or managing transactions.
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e2fac0819089b522db3260028c |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 8:08 p.m.