Triple
T28981438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lý Thánh Tông |
E734558
|
entity |
| Predicate | previousCountryName |
P33813
|
FINISHED |
| Object | Đại Cồ Việt |
—
|
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: Đại Cồ Việt | Statement: [Lý Thánh Tông, previousCountryName, Đại Cồ Việt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousCountryName Context triple: [Lý Thánh Tông, previousCountryName, Đại Cồ Việt]
-
A.
previousCountry
Indicates that one country was the immediately preceding country associated with, visited by, or occupied by a given entity before its current country.
-
B.
cedingCountry
Indicates the country that transfers or relinquishes control, ownership, or sovereignty over a territory, right, or asset to another party.
-
C.
formerHostCountry
Indicates that one entity was previously the host country for another entity, but no longer holds that role.
-
D.
formerGoverningCountry
Indicates that one country previously held governing or colonial authority over another country or territory.
-
E.
previousNameOfCountry
chosen
Indicates that one country name was formerly used as the official name of another 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_69f05b0dd9b481908b7901e1c95ff6b2 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: April 28, 2026, 9:11 a.m.