Triple
T38271051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lo Wu Control Point |
E1021207
|
entity |
| Predicate | borderDirectionFromHongKong |
P201923
|
FINISHED |
| Object | north |
—
|
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: north | Statement: [Lo Wu Control Point, borderDirectionFromHongKong, north]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderDirectionFromHongKong Context triple: [Lo Wu Control Point, borderDirectionFromHongKong, north]
-
A.
borderDirectionFromGuangzhou
Indicates the cardinal or relative direction in which another region or entity lies when measured from Guangzhou’s borders.
-
B.
borderDirectionFromSingapore
Indicates the directional orientation of another location’s border relative to Singapore.
-
C.
borderDirectionFromCapital
Indicates the compass direction from a country's capital city to a specified border or neighboring entity.
-
D.
borderDirectionFromUS
Indicates the compass direction in which a country or region lies relative to the United States along their shared border.
-
E.
borderTypeWithChina
Indicates the type or nature of the border relationship an entity has with China.
- F. None of above. chosen
Provenance (4 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_69f76dee198c8190bf5109421e47a658 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0031ed5d708190ab93516ad081ada6 |
completed | May 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_6a0031b5dbd081908eb0f4dbb8a0eac3 |
completed | May 10, 2026, 7:20 a.m. |
| PDg | Predicate description generation | batch_6a0031ec758c81908a3877bc19ce2701 |
completed | May 10, 2026, 7:21 a.m. |
Created at: May 3, 2026, 4:30 p.m.