Triple
T12899159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | pdfTeX |
E308571
|
entity |
| Predicate | developer |
P73
|
FINISHED |
| Object | Hàn Thế Thành |
E1008095
|
NE 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: Hàn Thế Thành | Statement: [pdfTeX, developer, Hàn Thế Thành]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hàn Thế Thành Context triple: [pdfTeX, developer, Hàn Thế Thành]
-
A.
Hàn Thế Thành
chosen
Hàn Thế Thành is a Vietnamese computer scientist best known for developing pdfTeX, an extended version of TeX that outputs PDF directly.
-
B.
Pham Hung
Pham Hung was a Vietnamese communist revolutionary and politician who served as Prime Minister of Vietnam in the late 1980s.
-
C.
Nguyễn Thanh Hưng
Nguyễn Thanh Hưng is a Vietnamese professional known as a graduate of the prestigious Foreign Trade University, often associated with careers in business, economics, or international trade.
-
D.
Ngo Kien Huy
Ngo Kien Huy is a Vietnamese pop singer, actor, and television host known for his energetic performances and appearances in popular entertainment shows.
-
E.
Ngo Tuan Anh
Ngo Tuan Anh is a Vietnamese individual notable enough to be recognized as a prominent bearer of the surname Ngo.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9717f3fc48190b61c8f6f36cd0725 |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6af59f3cc81908c99bcde43e724e6 |
completed | May 3, 2026, 2:13 a.m. |
Created at: April 9, 2026, 5:40 p.m.