Triple
T38271089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man Kam To Control Point |
E1021208
|
entity |
| Predicate | adjacentJurisdiction |
P91381
|
FINISHED |
| Object | Shenzhen Municipality |
—
|
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: Shenzhen Municipality | Statement: [Man Kam To Control Point, adjacentJurisdiction, Shenzhen Municipality]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentJurisdiction Context triple: [Man Kam To Control Point, adjacentJurisdiction, Shenzhen Municipality]
-
A.
hasAdjacentJurisdiction
chosen
Indicates that one jurisdiction directly borders or is immediately next to another jurisdiction.
-
B.
hasNearbyJurisdiction
Indicates that one jurisdiction is geographically close to or adjacent to another jurisdiction.
-
C.
adjacentProvince
Indicates that two provinces share a common boundary and are directly next to each other geographically.
-
D.
territorialJurisdictionOf
Indicates that one entity has legal or administrative authority over a specific geographic area or territory associated with another entity.
-
E.
sisterJurisdiction
Indicates that two jurisdictions are related at a similar hierarchical level, typically within the same broader system, without one having authority over the other.
- 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_69f76dee198c8190bf5109421e47a658 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd6a1c1c4881908090053bc359b181 |
completed | May 8, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69fd696f24d8819091033afacbdaadc5 |
completed | May 8, 2026, 4:41 a.m. |
Created at: May 3, 2026, 4:30 p.m.