Triple
T1320111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Municipal Offices and Train Station Delft |
E28196
|
entity |
| Predicate | tracksLocation |
P26972
|
FINISHED |
| Object | underground rail tunnel |
—
|
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: underground rail tunnel | Statement: [Municipal Offices and Train Station Delft, tracksLocation, underground rail tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tracksLocation Context triple: [Municipal Offices and Train Station Delft, tracksLocation, underground rail tunnel]
-
A.
trackingType
Indicates the method or category by which an entity’s movement, status, or progress is monitored or recorded.
-
B.
track
Indicates that one entity follows, monitors, or keeps a record of another entity’s state, behavior, or progress over time.
-
C.
currentLocationSince
Indicates the point in time since which an entity has been at its current location.
-
D.
visitedLocation
Indicates that an entity has gone to or spent time at a particular location.
-
E.
coordinateLocation
Indicates that an entity is located at, or associated with, a specific geographic coordinate or set of coordinates.
- 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_69a498532c3481909223b74af2e578df |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c179883c8190b68fbeebb9696982 |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beebcb348190964bd7215811942c |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4bfc2134c81909cbaaa151d96e9a8 |
completed | March 1, 2026, 10:37 p.m. |
Created at: March 1, 2026, 7:55 p.m.