Triple
T23892158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hengshui Middle School |
E600796
|
entity |
| Predicate | targetUniversities |
P62952
|
FINISHED |
| Object | Tsinghua University |
—
|
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: Tsinghua University | Statement: [Hengshui Middle School, targetUniversities, Tsinghua University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetUniversities Context triple: [Hengshui Middle School, targetUniversities, Tsinghua University]
-
A.
countryUniversity
Indicates that a university is located in, or belongs to, a particular country.
-
B.
hostUniversity
Indicates that a university serves as the primary institution hosting, organizing, or providing the setting for a given entity or activity (such as a program, event, or affiliation).
-
C.
hasUniversities
chosen
Indicates that an entity possesses, contains, or is associated with one or more universities.
-
D.
publicUniversityType
Indicates that an institution is classified as a public university, typically funded and operated by government or state authorities.
-
E.
stateUniversity
Indicates that an institution is a university that is publicly funded and operated under the authority of a state or similar governmental entity.
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cd044708819091102ecc160e1961 |
completed | April 29, 2026, 9:19 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:25 p.m.