Triple
T11551102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Bend Airport station |
E273890
|
entity |
| Predicate | hasIndoorAccessTo |
P61429
|
FINISHED |
| Object | airport terminal building |
—
|
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: airport terminal building | Statement: [South Bend Airport station, hasIndoorAccessTo, airport terminal building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIndoorAccessTo Context triple: [South Bend Airport station, hasIndoorAccessTo, airport terminal building]
-
A.
hasIndoorType
Indicates that an entity is associated with a specific type or category of indoor environment or indoor feature.
-
B.
hasIndoorArea
chosen
Indicates that an entity possesses or includes an area or space that is located indoors or within a building.
-
C.
hasAmenityAccessTo
Indicates that an entity has the right or ability to use or benefit from a specified amenity or facility.
-
D.
indoorOrOutdoor
Indicates whether an activity, event, or entity occurs inside a building (indoors) or outside in open air (outdoors).
-
E.
hasDomeOrRoofAccess
Indicates that an entity has access to, or the ability to reach or use, a dome or roof area associated with 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88a83f1e88190aabf11a4c8a6c9e5 |
completed | April 10, 2026, 5:28 a.m. |
| PD | Predicate disambiguation | batch_69d8087e57b48190a4c253dc0210f9d4 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.