Triple
T8861623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tran Van Huong |
E210900
|
entity |
| Predicate | servedAsPrimeMinisterFrom |
P370
|
FINISHED |
| Object | 1964-11-04 |
—
|
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: 1964-11-04 | Statement: [Tran Van Huong, servedAsPrimeMinisterFrom, 1964-11-04]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedAsPrimeMinisterFrom Context triple: [Tran Van Huong, servedAsPrimeMinisterFrom, 1964-11-04]
-
A.
servedUnderPrimeMinister
Indicates that one person held a governmental or official position subordinate to, and during the tenure of, a particular prime minister.
-
B.
succeededInOfficeAsPrimeMinisterBy
Indicates that one individual’s term as Prime Minister ended and was directly followed by another individual’s term in that office.
-
C.
heldOfficeOfPrimeMinisterThrough
Indicates that an entity continuously occupied and exercised the role and responsibilities of Prime Minister throughout a specified time period.
-
D.
officeHeldAsPrimeMinister
Indicates that an individual holds or has held the specific office or position of Prime Minister.
-
E.
primeMinisterTermStart
chosen
Indicates the date on which an individual officially begins serving as prime minister.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60e860888190a8a8702377db949e |
completed | April 1, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69cc5c279ea481908c71756f694b66bf |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:50 p.m.