Triple
T23879537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suqian Economic and Technological Development Zone |
E600159
|
entity |
| Predicate | policySupportFrom |
P82446
|
FINISHED |
| Object | Jiangsu Provincial Government |
—
|
NE NERFINISHED |
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: Jiangsu Provincial Government | Statement: [Suqian Economic and Technological Development Zone, policySupportFrom, Jiangsu Provincial Government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policySupportFrom Context triple: [Suqian Economic and Technological Development Zone, policySupportFrom, Jiangsu Provincial Government]
-
A.
supportsPolicy
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
-
B.
partySupported
chosen
Indicates that one party or entity provides backing, endorsement, or assistance to another party or entity.
-
C.
supportRules
Indicates that one entity provides justification, backing, or validation for the rules or constraints defined by another entity.
-
D.
supportPolicy
Indicates that one entity endorses, backs, or helps to maintain a particular policy or course of action.
-
E.
policyResponseTo
Indicates a relationship where a policy is created, modified, or applied as a direct reaction to a specific event, condition, or prior action.
- 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_69e295318e148190b9979d8fc02e168f |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cc03fdcc8190ad77155ae7e6eda5 |
completed | April 29, 2026, 9:14 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:23 p.m.