Triple
T19927176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Station Square 1 |
E478954
|
entity |
| Predicate | isCentralNodeIn |
P20548
|
FINISHED |
| Object | Tbilisi public transport network |
—
|
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: Tbilisi public transport network | Statement: [Station Square 1, isCentralNodeIn, Tbilisi public transport network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCentralNodeIn Context triple: [Station Square 1, isCentralNodeIn, Tbilisi public transport network]
-
A.
isCentralTo
Indicates that something plays a primary, essential, or defining role in relation to something else, such that the latter depends on or is organized around it.
-
B.
isSelfCentralizingIn
Indicates that an entity is equal to its own centralizer within a larger structure, meaning all elements that commute with it are contained in it.
-
C.
hasCenterIn
Indicates that something is located, based, or primarily focused within a specified central place or area.
-
D.
isKeyNodeIn
chosen
Indicates that a node serves as a primary or critical element within a specified structure, system, or context.
-
E.
isNucleusOf
Indicates that one entity functions as the central or most important core component of 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659ca52c881908dc8053bf61be4c4 |
completed | April 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.