Triple
T9667666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haikou Special Economic Zone |
E233745
|
entity |
| Predicate | aimsToAttract |
P1347
|
FINISHED |
| Object | foreign direct investment |
—
|
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: foreign direct investment | Statement: [Haikou Special Economic Zone, aimsToAttract, foreign direct investment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimsToAttract Context triple: [Haikou Special Economic Zone, aimsToAttract, foreign direct investment]
-
A.
attracts
chosen
Indicates that one entity exerts a force or influence that draws another entity toward it.
-
B.
aimedAtBy
Indicates that one entity serves as the target or goal toward which another entity directs an action, intention, or focus.
-
C.
aimsToProvide
Indicates that one entity intends or is designed to supply, deliver, or make available something to another entity.
-
D.
attractsAudience
Indicates that an entity draws the interest or attention of people who choose to watch, listen to, or engage with it.
-
E.
aimOf
Indicates that one entity serves as the goal, purpose, or intended target of another entity’s action, plan, or existence.
- 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_69ca848d3b6c8190ae98ea554dea58df |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c3c06e4819080c1b8e66faa482f |
completed | April 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b3239c8190b3ae3b9bd121e4bd |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:15 p.m.