Triple
T22446402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xavier Leroy |
E554873
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Xavier Leroy |
—
|
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: Xavier Leroy | Statement: [Xavier Leroy, name, Xavier Leroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xavier Leroy Context triple: [Xavier Leroy, name, Xavier Leroy]
-
A.
Xavier Leroy
chosen
Xavier Leroy is a French computer scientist best known for his work on the OCaml programming language and the formally verified CompCert C compiler.
-
B.
Jeffrey Huet
Jeffrey Huet is a comic book inker known for his work on major Marvel titles, including the "Planet Hulk" storyline.
-
C.
Yves Bertot
Yves Bertot is a French computer scientist known for his work on formal methods and the Coq proof assistant.
-
D.
Gérard Berry
Gérard Berry is a prominent French computer scientist known for his pioneering work in programming languages, formal methods, and synchronous programming.
-
E.
Patrice Godefroid
Patrice Godefroid is a computer scientist known for his pioneering work in software model checking, automated testing, and program analysis.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4803908190990280ebd258cb03 |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:47 p.m.