Triple
T6563671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 蔚山 |
E153846
|
entity |
| Predicate | 人口特征 |
P2501
|
FINISHED |
| Object | 以产业工人为主 |
—
|
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: 以产业工人为主 | Statement: [蔚山, 人口特征, 以产业工人为主]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 人口特征 Context triple: [蔚山, 人口特征, 以产业工人为主]
-
A.
demographicsCharacteristic
Indicates that one entity serves as a demographic attribute or characteristic (such as age, gender, ethnicity, etc.) that describes or classifies another entity.
-
B.
demographicCharacteristic
chosen
Indicates that one entity specifies or describes a demographic attribute or feature (such as age, gender, ethnicity, or similar population-related trait) of another entity.
-
C.
populationClass
Indicates a categorical classification of a population based on shared characteristics, status, or demographic criteria.
-
D.
populationFocus
Indicates that something is primarily directed toward, concerned with, or designed for a particular population or demographic group.
-
E.
populationMeasurementBy
Indicates that a population quantity or statistic is determined, recorded, or reported by a specified agent, method, or source.
- 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_69c6880cb35881909b763eb0125236b9 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6acf93cb48190b54f5dd6febd34dc |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:52 p.m.