Triple
T31440877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sơn Tây ancient citadel |
E802061
|
entity |
| Predicate | distanceFromHanoiCenter |
P27403
|
FINISHED |
| Object | approximately 40 kilometers west |
—
|
LITERAL 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: approximately 40 kilometers west | Statement: [Sơn Tây ancient citadel, distanceFromHanoiCenter, approximately 40 kilometers west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromHanoiCenter Context triple: [Sơn Tây ancient citadel, distanceFromHanoiCenter, approximately 40 kilometers west]
-
A.
distanceFromHanoi
chosen
Indicates the spatial distance between a given location and Hanoi.
-
B.
distanceFromCanThoCenter
Indicates the measured spatial distance between a given location and the central point of Can Tho.
-
C.
distanceFromDaNangCenter
Indicates the spatial distance between an entity’s location and the central point of Da Nang.
-
D.
distanceFromHoiAnCenter
Indicates the measured distance between a given location and the central point of Hoi An.
-
E.
distanceToDaNang_km
Indicates the distance, measured in kilometers, between a given location and Da Nang.
- F. None of above.
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_69f348c5a6bc819092a557e95438976f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a01c51e2d088190b9dcce5b6de1cb9b |
completed | May 11, 2026, 12:01 p.m. |
| PD | Predicate disambiguation | batch_6a01c4c715a48190b7435de8a9d86fd4 |
completed | May 11, 2026, noon |
Created at: April 30, 2026, 9:05 p.m.