Triple
T28269451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republic of China politics |
E712803
|
entity |
| Predicate | countryCommonName |
P182829
|
FINISHED |
| Object | Taiwan |
—
|
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: Taiwan | Statement: [Republic of China politics, countryCommonName, Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryCommonName Context triple: [Republic of China politics, countryCommonName, Taiwan]
-
A.
countrySpecificName
Indicates that an entity has a name or label that is specific to, or used within, a particular country.
-
B.
commonNameCountry
chosen
Indicates that a given name is the commonly used or widely recognized name for a particular country.
-
C.
countryLabel
Indicates the name or label of the country associated with an entity.
-
D.
countryNameLocal
Indicates the name of a country as expressed in its own local or official language.
-
E.
countryNameInEnglish
Indicates the English-language name assigned to a given country.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
Created at: April 27, 2026, 11:17 p.m.