Triple
T21619337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame Nhu |
E533533
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Trần |
—
|
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: Trần | Statement: [Madame Nhu, familyName, Trần]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trần Context triple: [Madame Nhu, familyName, Trần]
-
A.
Nguyễn
Nguyễn is a common Vietnamese given name and surname widely used across Vietnam and among the Vietnamese diaspora.
-
B.
Trần Thủ Độ
Trần Thủ Độ was a powerful Vietnamese statesman and military leader who orchestrated the rise of the Trần dynasty and served as its de facto founding architect.
-
C.
Tran Quoc Hoan
Tran Quoc Hoan was a prominent Vietnamese communist politician who served as the first Minister of Public Security of North Vietnam.
-
D.
Tran
chosen
Tran is a personal name, commonly used as both a given name and surname in various cultures, particularly in East and Southeast Asia.
-
E.
Le Minh Tri
Le Minh Tri is a Vietnamese politician and jurist who has served as the head of Vietnam’s top prosecutorial and supervisory authority over legal compliance.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3bad094c8190879d4aef7988254a |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 16, 2026, 6:34 p.m.