Triple
T22701972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bolesław Leśmian |
E561346
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Lesman
Lesman is the family name of Bolesław Leśmian, a renowned Polish poet known for his innovative, imaginative verse and distinctive use of language.
|
E1550087
|
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: Lesman | Statement: [Bolesław Leśmian, familyName, Lesman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lesman Context triple: [Bolesław Leśmian, familyName, Lesman]
-
A.
Leeman
Leeman is the namesake of Leeman-Turner Arena at Grace Hall, likely a person honored for significant contributions to the associated institution or community.
-
B.
Leeman
Leeman is a small coastal town in the Mid West region of Western Australia, known for its fishing and relaxed seaside lifestyle.
-
C.
Leman Tomsu
Leman Tomsu was a pioneering Turkish architect and one of the first female architects in Turkey.
-
D.
Lehae
Lehae is a residential suburb located in the southern part of Johannesburg, South Africa.
-
E.
Teyjus
Teyjus is a software system that provides a concrete implementation of the LambdaProlog logic programming language, supporting higher-order and modular logic programming.
- 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: Lesman Triple: [Bolesław Leśmian, familyName, Lesman]
Generated description
Lesman is the family name of Bolesław Leśmian, a renowned Polish poet known for his innovative, imaginative verse and distinctive use of language.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lesman Target entity description: Lesman is the family name of Bolesław Leśmian, a renowned Polish poet known for his innovative, imaginative verse and distinctive use of language.
-
A.
Leeman
Leeman is a small coastal town in the Mid West region of Western Australia, known for its fishing and relaxed seaside lifestyle.
-
B.
Leeman
Leeman is the namesake of Leeman-Turner Arena at Grace Hall, likely a person honored for significant contributions to the associated institution or community.
-
C.
Leman Tomsu
Leman Tomsu was a pioneering Turkish architect and one of the first female architects in Turkey.
-
D.
Lehae
Lehae is a residential suburb located in the southern part of Johannesburg, South Africa.
-
E.
Teyjus
Teyjus is a software system that provides a concrete implementation of the LambdaProlog logic programming language, supporting higher-order and modular logic programming.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cb2f548190bfc6f050be7c795a |
completed | April 29, 2026, 3:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b7ed40b5c8190a2ac99d215de0c31 |
completed | May 18, 2026, 9:04 p.m. |
| NEDg | Description generation | batch_6a0b7f9ccb00819092fe5e9d71f545e4 |
completed | May 18, 2026, 9:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b806b4e1481909babc97a8914947a |
completed | May 18, 2026, 9:11 p.m. |
Created at: April 17, 2026, 3:16 p.m.