Triple
T19634102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom B. Brown |
E471343
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object | Mateusz Litwin |
—
|
NE NERFINISHED |
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: Mateusz Litwin | Statement: [Tom B. Brown, coAuthorWith, Mateusz Litwin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mateusz Litwin Context triple: [Tom B. Brown, coAuthorWith, Mateusz Litwin]
-
A.
Mateusz Litwin
chosen
Mateusz Litwin is a researcher known for co-authoring influential work in large-scale machine learning and language models alongside Tom B. Brown.
-
B.
Mateusz Litwin
Mateusz Litwin is a computer scientist and researcher known for co-authoring influential work in artificial intelligence and machine learning alongside Benjamin Chess.
-
C.
Mateusz Dróżdż
Mateusz Dróżdż is a Polish football executive best known for serving as chairman of the historic club Widzew Łódź.
-
D.
Maciej Rataj
Maciej Rataj was a prominent Polish politician and statesman, twice acting President of Poland during the interwar period and a leading figure of the Polish People's Party.
-
E.
Radosław Dobrowolski
Radosław Dobrowolski is a Polish academic and administrator who serves as the rector of Maria Curie-Skłodowska University in Lublin.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64104ff2881908fec49b7fba5a2e6 |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:44 p.m.