Triple
T17849431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Puhuangyu station |
E445756
|
entity |
| Predicate | hasStationCodeLine14 |
P1289
|
FINISHED |
| Object | Line 14 station code (Beijing Subway) |
—
|
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: Line 14 station code (Beijing Subway) | Statement: [Puhuangyu station, hasStationCodeLine14, Line 14 station code (Beijing Subway)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStationCodeLine14 Context triple: [Puhuangyu station, hasStationCodeLine14, Line 14 station code (Beijing Subway)]
-
A.
hasStationCode
chosen
Indicates that an entity is associated with a specific station identification code.
-
B.
hasStationCodeSystem
Indicates that an entity uses or is associated with a particular system for assigning or managing station codes.
-
C.
hasStationCodeInternal
Indicates that an entity is associated with a specific internal station code used within a system or organization.
-
D.
hasAdjacentStationOnLine12
Indicates that one station is directly next to another station along transit line 12, with no other stations in between on that line.
-
E.
hasAdjacentStationOnLine4
Indicates that one station is directly next to another station along transit line 4.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ffd7e2c81909a42cc7ab64e7db9 |
completed | April 19, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e266888190ae976b4b7d5b886f |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:16 a.m.