Triple
T18930475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nunnery Square depot |
E463093
|
entity |
| Predicate | hasTypeOfTracks |
P3832
|
FINISHED |
| Object | depot sidings |
—
|
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: depot sidings | Statement: [Nunnery Square depot, hasTypeOfTracks, depot sidings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfTracks Context triple: [Nunnery Square depot, hasTypeOfTracks, depot sidings]
-
A.
hasTrack
Indicates that one entity possesses, includes, or is associated with a specific track (such as a path, course, or recorded item).
-
B.
hasTrackFeatures
Indicates that something possesses or is associated with specific track-related characteristics or attributes.
-
C.
trackType
chosen
Indicates the specific kind or category of track associated with an entity, such as its functional or physical classification.
-
D.
hasTailTracks
Indicates that an entity exhibits or leaves behind tail-shaped tracks or imprints as evidence of its movement or presence.
-
E.
hasTwoTracks
Indicates that the subject possesses or is associated with exactly two distinct tracks or pathways.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c9bfaee881908d701c5a05528939 |
completed | April 20, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 11:59 a.m.