Triple
T3888973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tea Horse Road |
E88010
|
entity |
| Predicate | tradeDirection |
P40844
|
FINISHED |
| Object | tea from China to Tibet |
—
|
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: tea from China to Tibet | Statement: [Tea Horse Road, tradeDirection, tea from China to Tibet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tradeDirection Context triple: [Tea Horse Road, tradeDirection, tea from China to Tibet]
-
A.
trades
Indicates an exchange relationship where one party gives something of value to another in return for something else of value.
-
B.
tradedTo
Indicates that ownership or contractual rights to an entity (such as a player, asset, or item) were transferred from one party to another, typically as part of an exchange or deal.
-
C.
tradeSystem
Indicates a system or framework through which goods, services, or assets are exchanged between parties under defined rules or mechanisms.
-
D.
tradesAs
Indicates that one entity conducts business or is publicly known under the trading name or brand of another entity.
-
E.
transactionNature
chosen
Indicates the type or character of a transaction, specifying what kind of exchange or operation is taking place between the involved parties.
- 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_69aed9466d548190939f5217a23ed4ac |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecad4bf081909ae45a69d22468fa |
completed | March 9, 2026, 3:52 p.m. |
| PD | Predicate disambiguation | batch_69aee759609c8190985e96ec6d96dedd |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:21 p.m.