Triple
T22446419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xavier Leroy |
E554873
|
entity |
| Predicate | developed |
P73
|
FINISHED |
| Object |
CompCert
CompCert is a formally verified optimizing C compiler designed to provide mathematically proven correctness guarantees for safety- and mission-critical software.
|
E1536608
|
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: CompCert | Statement: [Xavier Leroy, developed, CompCert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CompCert Context triple: [Xavier Leroy, developed, CompCert]
-
A.
Cyert
Cyert is a surname most notably associated with Richard M. Cyert, an influential American economist and former president of Carnegie Mellon University.
-
B.
JProof
JProof is a music producer known for his work on Usher’s album "Hard II Love."
-
C.
Certified
"Certified" is a studio album by American rapper and producer David Banner that showcases his Southern hip hop style and socially conscious themes.
-
D.
Compans
Compans is a small French commune located in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
-
E.
Com
Com is a small coastal village in eastern Timor-Leste known for its beaches, fishing community, and growing eco-tourism.
- 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: CompCert Triple: [Xavier Leroy, developed, CompCert]
Generated description
CompCert is a formally verified optimizing C compiler designed to provide mathematically proven correctness guarantees for safety- and mission-critical software.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CompCert Target entity description: CompCert is a formally verified optimizing C compiler designed to provide mathematically proven correctness guarantees for safety- and mission-critical software.
-
A.
Cyert
Cyert is a surname most notably associated with Richard M. Cyert, an influential American economist and former president of Carnegie Mellon University.
-
B.
JProof
JProof is a music producer known for his work on Usher’s album "Hard II Love."
-
C.
Certified
"Certified" is a studio album by American rapper and producer David Banner that showcases his Southern hip hop style and socially conscious themes.
-
D.
Compans
Compans is a small French commune located in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
-
E.
Com
Com is a small coastal village in eastern Timor-Leste known for its beaches, fishing community, and growing eco-tourism.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4803908190990280ebd258cb03 |
completed | April 29, 2026, 1:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b0c7640fc8190a2dd1643a7c2a5b0 |
completed | May 18, 2026, 12:56 p.m. |
| NEDg | Description generation | batch_6a0b0cd3f7bc8190bdc1e241ea1c642f |
completed | May 18, 2026, 12:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b0d40e0c8819083a430e30dba1848 |
completed | May 18, 2026, 12:59 p.m. |
Created at: April 16, 2026, 8:47 p.m.