Triple
T38271090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man Kam To Control Point |
E1021208
|
entity |
| Predicate | adjacentControlPoint |
P194405
|
FINISHED |
| Object | Wenjindu Port |
—
|
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: Wenjindu Port | Statement: [Man Kam To Control Point, adjacentControlPoint, Wenjindu Port]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentControlPoint Context triple: [Man Kam To Control Point, adjacentControlPoint, Wenjindu Port]
-
A.
adjacentLandmark
Indicates that one landmark is located directly next to or very near another landmark, with no significant separation between them.
-
B.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
C.
adjacentIslandArc
Indicates that one island arc is directly next to or bordering another island arc in geographic space.
-
D.
adjacentLine
Indicates that one line is directly next to another line, sharing a common boundary or position without overlapping.
-
E.
adjacentPlanePrevious
Indicates that one plane is directly next to another plane and comes immediately before it in a defined ordering or sequence.
- 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_69fd6dbd1b648190b1a0b391c03aebc5 |
completed | May 8, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69fd6a9020548190bbfa845360ac85fb |
completed | May 8, 2026, 4:46 a.m. |
| PDg | Predicate description generation | batch_69fd6dbc3ac0819093fbcfe95f12b93d |
completed | May 8, 2026, 4:59 a.m. |
Created at: May 3, 2026, 4:30 p.m.