Triple
T28900999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taiwan semiconductor cluster |
E732948
|
entity |
| Predicate | includesSciencePark |
P32590
|
FINISHED |
| Object | Hsinchu Science Park |
—
|
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: Hsinchu Science Park | Statement: [Taiwan semiconductor cluster, includesSciencePark, Hsinchu Science Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesSciencePark Context triple: [Taiwan semiconductor cluster, includesSciencePark, Hsinchu Science Park]
-
A.
hasSciencePark
chosen
Indicates that one entity possesses, hosts, or includes a science park associated with it.
-
B.
isScienceCity
Indicates that a city is recognized or designated as a center for scientific research, education, or technological innovation.
-
C.
locatedInScienceCity
Indicates that one entity is situated within or belongs to the geographic or administrative area designated as a science city.
-
D.
hasScienceCenter
Indicates that an entity possesses, hosts, or includes a science center as one of its facilities or components.
-
E.
inPark
Indicates that one entity is located within or inside the boundaries of a park.
- 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_69f05b08c2008190ac426a035a2ed66d |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69ff53389a0481908b2baeb43c6294f0 |
completed | May 9, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69ff52e2b4b88190b38d160d771fe14b |
completed | May 9, 2026, 3:29 p.m. |
Created at: April 28, 2026, 8:02 a.m.