Triple
T8907988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kharkiv Metro |
E212108
|
entity |
| Predicate | hasDepot |
P2413
|
FINISHED |
| Object |
Saltivske depot
Saltivske depot is a major maintenance and storage facility serving the Kharkiv Metro system in Kharkiv, Ukraine.
|
E765653
|
NE FINISHED |
How this triple was built (4 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: Saltivske depot | Statement: [Kharkiv Metro, hasDepot, Saltivske depot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saltivske depot Context triple: [Kharkiv Metro, hasDepot, Saltivske depot]
-
A.
Carnide depot
Carnide depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
-
B.
Berceni depot
Berceni depot is a maintenance and storage facility serving the Bucharest Metro system in Bucharest, Romania.
-
C.
Vennes depot
Vennes depot is a maintenance and storage facility serving Lausanne’s metro system in Switzerland.
-
D.
Gogar depot
Gogar depot is the main maintenance and operations facility for the Edinburgh Trams light rail system in Edinburgh, Scotland.
-
E.
Lagery
Lagery is a small commune in northeastern France best known as the birthplace of Pope Urban II, who launched the First Crusade.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Saltivske depot Triple: [Kharkiv Metro, hasDepot, Saltivske depot]
Generated description
Saltivske depot is a major maintenance and storage facility serving the Kharkiv Metro system in Kharkiv, Ukraine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saltivske depot Target entity description: Saltivske depot is a major maintenance and storage facility serving the Kharkiv Metro system in Kharkiv, Ukraine.
-
A.
Carnide depot
Carnide depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
-
B.
Berceni depot
Berceni depot is a maintenance and storage facility serving the Bucharest Metro system in Bucharest, Romania.
-
C.
Vennes depot
Vennes depot is a maintenance and storage facility serving Lausanne’s metro system in Switzerland.
-
D.
Gogar depot
Gogar depot is the main maintenance and operations facility for the Edinburgh Trams light rail system in Edinburgh, Scotland.
-
E.
Lagery
Lagery is a small commune in northeastern France best known as the birthplace of Pope Urban II, who launched the First Crusade.
- F. None of above. chosen
Provenance (5 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_69ca839255248190b43984294abd92ae |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc64c6a87c81909331a39619f913c0 |
completed | April 1, 2026, 12:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba31fc148190a8dbe378694dcc32 |
completed | April 3, 2026, 1:01 p.m. |
| NEDg | Description generation | batch_69cfbabf33a08190a18d13b9078c00e2 |
completed | April 3, 2026, 1:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfbba71a948190afc03a1df9e5777c |
completed | April 3, 2026, 1:07 p.m. |
Created at: March 30, 2026, 6:55 p.m.