Triple
T9874895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perm Krai |
E240048
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object |
Lysva
Lysva is an industrial city in Perm Krai, Russia, historically known for its metallurgical and machine-building industries.
|
E826715
|
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: Lysva | Statement: [Perm Krai, hasCity, Lysva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lysva Context triple: [Perm Krai, hasCity, Lysva]
-
A.
River Isbourne
River Isbourne is a small river in Gloucestershire, England, flowing through the Cotswolds and the town of Winchcombe before joining the River Avon.
-
B.
Lindaunis
Lindaunis is a small village in northern Germany situated along the Schlei inlet in the state of Schleswig-Holstein.
-
C.
Lunan Water
Lunan Water is a river in Angus, Scotland, that flows into the North Sea at the scenic Lunan Bay.
-
D.
Hermitage Water
Hermitage Water is a river in the Scottish Borders that flows past the historic Hermitage Castle and through a remote, rural valley.
-
E.
The Lakes
The Lakes is an upscale residential community in Dubai known for its landscaped lakes, family-friendly environment, and proximity to major developments like Emirates Hills.
- 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: Lysva Triple: [Perm Krai, hasCity, Lysva]
Generated description
Lysva is an industrial city in Perm Krai, Russia, historically known for its metallurgical and machine-building industries.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lysva Target entity description: Lysva is an industrial city in Perm Krai, Russia, historically known for its metallurgical and machine-building industries.
-
A.
River Isbourne
River Isbourne is a small river in Gloucestershire, England, flowing through the Cotswolds and the town of Winchcombe before joining the River Avon.
-
B.
Lindaunis
Lindaunis is a small village in northern Germany situated along the Schlei inlet in the state of Schleswig-Holstein.
-
C.
Lunan Water
Lunan Water is a river in Angus, Scotland, that flows into the North Sea at the scenic Lunan Bay.
-
D.
Hermitage Water
Hermitage Water is a river in the Scottish Borders that flows past the historic Hermitage Castle and through a remote, rural valley.
-
E.
The Lakes
The Lakes is an upscale residential community in Dubai known for its landscaped lakes, family-friendly environment, and proximity to major developments like Emirates Hills.
- 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_69ca84e8a0788190b9061811d50fd554 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3f9d82c81908afb4977ce4e3e4a |
completed | April 2, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1e47515788190b6644021e187e771 |
completed | April 5, 2026, 4:26 a.m. |
| NEDg | Description generation | batch_69d1e57366748190bf617374264d1873 |
completed | April 5, 2026, 4:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1e5ed9818819095119c3478f97419 |
completed | April 5, 2026, 4:32 a.m. |
Created at: March 30, 2026, 8:37 p.m.