Triple
T27535901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianjin Port Free Trade Zone |
E695096
|
entity |
| Predicate | hasPreferentialPolicyType |
P32149
|
FINISHED |
| Object | trade policy |
—
|
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: trade policy | Statement: [Tianjin Port Free Trade Zone, hasPreferentialPolicyType, trade policy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreferentialPolicyType Context triple: [Tianjin Port Free Trade Zone, hasPreferentialPolicyType, trade policy]
-
A.
hasTypeOfPreference
chosen
Indicates that an entity holds a particular kind or category of preference toward something.
-
B.
hasPolicyInstrumentType
Indicates that a policy or measure is associated with a specific type or category of policy instrument used to implement it.
-
C.
typeOfTariffPreference
Indicates the specific category or kind of tariff preference applied within a trade or customs context.
-
D.
isPreferredWhen
Indicates that one option, condition, or entity is chosen or favored over others in a particular context or situation.
-
E.
hasBenefitType
Indicates that an entity is associated with a specific category or type of benefit it provides or receives.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fdec5ffe088190ac5505f26c6cff18 |
completed | May 8, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69fdeae15f1c81908fc63fbc1b028d2e |
completed | May 8, 2026, 1:53 p.m. |
Created at: April 27, 2026, 1:28 p.m.