Triple
T13561609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tbilisi funicular |
E323920
|
entity |
| Predicate | hasUpperStationFacility |
P110369
|
FINISHED |
| Object | restaurants |
—
|
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: restaurants | Statement: [Tbilisi funicular, hasUpperStationFacility, restaurants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUpperStationFacility Context triple: [Tbilisi funicular, hasUpperStationFacility, restaurants]
-
A.
upperStation
Indicates that one station is positioned higher or upstream in a system or hierarchy relative to another station.
-
B.
hasLowerStation
Indicates that one entity occupies a lower rank, status, or position in a hierarchy relative to another entity.
-
C.
hasUpperFloorUse
Indicates that an entity’s upper floor is assigned or designated for a particular use or function.
-
D.
hasUpperFloor
Indicates that one entity possesses or includes an upper floor relative to another level or reference point.
-
E.
hasRailFacility
Indicates that an entity possesses or is served by a rail-related facility, such as a railway station, terminal, or yard.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbb9ee3f081909056dc1a92c40b7a |
completed | April 12, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69dbae13bec4819084c1770638c00ed9 |
completed | April 12, 2026, 2:37 p.m. |
| PDg | Predicate description generation | batch_69dbbb8c77dc8190b7bd803b5e168d23 |
completed | April 12, 2026, 3:34 p.m. |
Created at: April 9, 2026, 9:47 p.m.