Triple
T20534671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tôn Đức Thắng |
E504161
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Tôn
Tôn is a Vietnamese surname most notably borne by Tôn Đức Thắng, a prominent revolutionary and former president of Vietnam.
|
E1435384
|
NE FINISHED |
How this triple was built (4 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: Tôn | Statement: [Tôn Đức Thắng, familyName, Tôn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tôn Context triple: [Tôn Đức Thắng, familyName, Tôn]
-
A.
Ha Tien
Ha Tien is a coastal town in Vietnam’s Mekong Delta known for its beaches, limestone landscapes, and proximity to the Cambodian border.
-
B.
Henao
Henao is a Spanish-language surname most notably associated with Maria Victoria Henao, the widow of Colombian drug lord Pablo Escobar.
-
C.
Hoan
Hoan is a surname most notably associated with Daniel Hoan, a long-serving Socialist mayor of Milwaukee in the early 20th century.
-
D.
Tuoba
Tuoba was the ruling clan of Xianbei origin that founded and led the Northern Wei dynasty in early medieval China.
-
E.
Xuan Dieu
Xuan Dieu is a popular street and neighborhood in Hanoi’s Tay Ho District, known for its lakeside views, expatriate community, and vibrant mix of cafes, restaurants, and shops.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tôn Triple: [Tôn Đức Thắng, familyName, Tôn]
Generated description
Tôn is a Vietnamese surname most notably borne by Tôn Đức Thắng, a prominent revolutionary and former president of Vietnam.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tôn Target entity description: Tôn is a Vietnamese surname most notably borne by Tôn Đức Thắng, a prominent revolutionary and former president of Vietnam.
-
A.
Ha Tien
Ha Tien is a coastal town in Vietnam’s Mekong Delta known for its beaches, limestone landscapes, and proximity to the Cambodian border.
-
B.
Henao
Henao is a Spanish-language surname most notably associated with Maria Victoria Henao, the widow of Colombian drug lord Pablo Escobar.
-
C.
Hoan
Hoan is a surname most notably associated with Daniel Hoan, a long-serving Socialist mayor of Milwaukee in the early 20th century.
-
D.
Tuoba
Tuoba was the ruling clan of Xianbei origin that founded and led the Northern Wei dynasty in early medieval China.
-
E.
Xuan Dieu
Xuan Dieu is a popular street and neighborhood in Hanoi’s Tay Ho District, known for its lakeside views, expatriate community, and vibrant mix of cafes, restaurants, and shops.
- F. None of above. chosen
Provenance (5 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06df04081908fa95c6214f06093 |
completed | April 20, 2026, 9:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a089d4c1a2c8190a8d6d6e19e67942f |
completed | May 16, 2026, 4:37 p.m. |
| NEDg | Description generation | batch_6a089e1dc3048190abb1c0bad8d4a3ed |
completed | May 16, 2026, 4:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a089ea8b9808190a20982193eaf9e22 |
completed | May 16, 2026, 4:43 p.m. |
Created at: April 16, 2026, 11:37 a.m.