Triple
T1861724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alonzo Church |
E34828
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | lambda calculus |
E26971
|
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: lambda calculus | Statement: [Alonzo Church, notableWork, lambda calculus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: lambda calculus Context triple: [Alonzo Church, notableWork, lambda calculus]
-
A.
lambda calculus
chosen
Lambda calculus is a formal system in mathematical logic and computer science that uses function abstraction and application to investigate computation and serves as a foundational model for programming languages.
-
B.
Lambda
Lambda is a General Motors mid-size crossover SUV platform used for vehicles such as the Saturn Outlook.
-
C.
Curry encoding
Curry encoding is a technique in lambda calculus for representing data structures and algebraic types purely as higher-order functions.
-
D.
Church–Rosser property
The Church–Rosser property is a confluence property of rewriting systems stating that if an expression can be reduced in different ways, all reduction paths can be further reduced to a common equivalent form.
-
E.
LambdaProlog
LambdaProlog is a logic programming language that extends Prolog with higher-order features, polymorphism, and strong support for reasoning about formal systems and syntax with bindings.
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb09e714881909cef0f7e77b5b3b9 |
completed | March 7, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69add1d026748190a507872de85c908d |
completed | March 8, 2026, 7:45 p.m. |
Created at: March 4, 2026, 7:34 p.m.