Triple
T9810246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Markus Wenzel |
E238249
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Isabelle/Isar |
E822910
|
NE FINISHED |
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: Isabelle/Isar | Statement: [Markus Wenzel, notableWork, Isabelle/Isar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isabelle/Isar Context triple: [Markus Wenzel, notableWork, Isabelle/Isar]
-
A.
Isabelle/Isar Reference Manual
The Isabelle/Isar Reference Manual is the official technical guide detailing the structured proof language Isar used within the Isabelle interactive theorem prover.
-
B.
Isar proof language
chosen
The Isar proof language is a human-readable, structured language for writing formal proofs within the Isabelle/HOL proof assistant.
-
C.
Isabelle proof assistant
Isabelle proof assistant is a widely used interactive theorem prover and generic proof assistant designed for formal verification and mathematical logic, particularly known for its support of higher-order logic.
-
D.
Isabelle/ML
Isabelle/ML is the ML-based implementation and extension language used to develop and script the Isabelle interactive theorem prover.
-
E.
Isabelle/FOL
Isabelle/FOL is the classical first-order logic object logic of the Isabelle proof assistant, providing a framework for formalizing and verifying mathematical theorems and logical systems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb220310c8190a16ca0b746f0ef7a |
completed | April 2, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5b264c88190bf16c8c32c360878 |
completed | April 5, 2026, 3:23 a.m. |
Created at: March 30, 2026, 8:30 p.m.