Triple
T21354786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tobolsk |
E526588
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object |
Upper Town
Upper Town is the historic elevated district of Tobolsk, known for its old architecture and administrative and religious landmarks.
|
E1479848
|
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: Upper Town | Statement: [Tobolsk, hasDivision, Upper Town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upper Town Context triple: [Tobolsk, hasDivision, Upper Town]
-
A.
Upper Town
Upper Town is the historic core of Belgrade Fortress, featuring ancient ramparts, gates, and landmarks overlooking the confluence of the Sava and Danube rivers.
-
B.
Upper Town
Upper Town is a district or neighborhood within Oranjestad, the capital city of Aruba.
-
C.
Upper Town
Upper Town is the historic elevated district of Sibiu, Romania, known for its medieval fortifications, grand squares, and well-preserved architecture.
-
D.
Upper Town
Upper Town is the historic fortified upper quarter of the medieval Greek town of Monemvasia, known for its Byzantine ruins and panoramic views over the sea.
-
E.
Upper Town
Upper Town is the English translation of "Dalt Vila," the historic fortified old town of Ibiza City, known for its Renaissance walls and UNESCO World Heritage status.
- 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: Upper Town Triple: [Tobolsk, hasDivision, Upper Town]
Generated description
Upper Town is the historic elevated district of Tobolsk, known for its old architecture and administrative and religious landmarks.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Upper Town Target entity description: Upper Town is the historic elevated district of Tobolsk, known for its old architecture and administrative and religious landmarks.
-
A.
Upper Town
Upper Town is the historic core of Belgrade Fortress, featuring ancient ramparts, gates, and landmarks overlooking the confluence of the Sava and Danube rivers.
-
B.
Upper Town
Upper Town is a district or neighborhood within Oranjestad, the capital city of Aruba.
-
C.
Upper Town
Upper Town is the historic elevated district of Sibiu, Romania, known for its medieval fortifications, grand squares, and well-preserved architecture.
-
D.
Upper Town
Upper Town is the historic fortified upper quarter of the medieval Greek town of Monemvasia, known for its Byzantine ruins and panoramic views over the sea.
-
E.
Upper Town
Upper Town is the English translation of "Dalt Vila," the historic fortified old town of Ibiza City, known for its Renaissance walls and UNESCO World Heritage status.
- 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_69e0b51cd5cc81909ac1187971e8a8ad |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8af9be3a48190aa8e6e9a5b812981 |
completed | April 22, 2026, 11:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09ad6361b881908db56803d3109bf4 |
completed | May 17, 2026, 11:58 a.m. |
| NEDg | Description generation | batch_6a09adf244d481908bb02f99844f1cd0 |
completed | May 17, 2026, noon |
| NED2 | Entity disambiguation (via description) | batch_6a09ae91d9cc8190a677124f1a0e1e4e |
completed | May 17, 2026, 12:03 p.m. |
Created at: April 16, 2026, 5:06 p.m.