Triple
T6263217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lin Zexu |
E140349
|
entity |
| Predicate | placeOfActivity |
P1527
|
FINISHED |
| Object | Humen |
E140348
|
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: Humen | Statement: [Lin Zexu, placeOfActivity, Humen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Humen Context triple: [Lin Zexu, placeOfActivity, Humen]
-
A.
Humen
chosen
Humen is a town in Guangdong, China, historically significant as a strategic Pearl River Delta port and a key site in the events leading to the First Opium War.
-
B.
Beitbridge
Beitbridge is a border town in southern Zimbabwe that serves as a major crossing point between Zimbabwe and South Africa.
-
C.
Dundas
Dundas is a Scottish surname historically associated with a prominent Lowland family influential in politics, law, and public life in Britain.
-
D.
Lobethal
Lobethal is a small town in South Australia known for its German heritage and popular annual Christmas lights festival.
-
E.
Port Henry
Port Henry is a small lakeside community in New York State known for its historic charm and location along the western shore of Lake Champlain.
- 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_69c008c95c5c819084bd3dd56133d84d |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06387fec0819095b47a37b9402aa9 |
completed | March 22, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c2445061a481909487fdb04c50493b |
completed | March 24, 2026, 7:59 a.m. |
Created at: March 22, 2026, 4:25 p.m.