Triple
T23097140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dong Ha |
E575922
|
entity |
| Predicate | locatedNorthOf |
P305
|
FINISHED |
| Object | Hue |
—
|
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: Hue | Statement: [Dong Ha, locatedNorthOf, Hue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hue Context triple: [Dong Ha, locatedNorthOf, Hue]
-
A.
Hue
chosen
Hue is a historic city in central Vietnam that served as the former imperial capital and was a major battleground during the Vietnam War.
-
B.
Buren
Buren is a historic Dutch town in the province of Gelderland, known for its ties to the Dutch royal family and its well-preserved medieval character.
-
C.
Buren
Buren is the entomologist who formally described the invasive red imported fire ant species Solenopsis invicta.
-
D.
Barvas
Barvas is a coastal village and community on the Isle of Lewis in Scotland’s Outer Hebrides, known for its Gaelic heritage and traditional crofting landscape.
-
E.
Ruit
Ruit is a locality or district that forms part of the town of Bretten in the state of Baden-Württemberg, Germany.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de61c7c8190809920fa1071935f |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:57 p.m.