Triple
T25180137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desiro City |
E630559
|
entity |
| Predicate | hasDoorOperation |
P154922
|
FINISHED |
| Object | power‑operated sliding plug doors |
—
|
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: power‑operated sliding plug doors | Statement: [Desiro City, hasDoorOperation, power‑operated sliding plug doors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDoorOperation Context triple: [Desiro City, hasDoorOperation, power‑operated sliding plug doors]
-
A.
hasDoorsOperation
chosen
Indicates that an entity has a specific type or mode of operation for its doors (e.g., how they open, close, or are controlled).
-
B.
hasDoor
Indicates that one entity possesses or is equipped with a door that provides access to or through it.
-
C.
hasDoors
Indicates that an object or structure possesses one or more doors.
-
D.
hasDoorGuard
Indicates that an entity has another entity serving as a guard for its door or entrance.
-
E.
hasDoorSide
Indicates that one entity represents a specific side or face of a door in relation to another entity.
- 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_69e75a88fdf081908e47ae6e195c14e1 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46dc4c3308190b9cb0ff4cbdc08d5 |
completed | May 1, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:35 p.m.