Triple
T9810259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Markus Wenzel |
E238249
|
entity |
| Predicate | worksOn |
P3
|
FINISHED |
| Object | Isabelle documentation |
E386747
|
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 documentation | Statement: [Markus Wenzel, worksOn, Isabelle documentation]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isabelle documentation Context triple: [Markus Wenzel, worksOn, Isabelle documentation]
-
A.
Isabelle
chosen
Isabelle is a popular character from the Animal Crossing series who also appears as a playable racer in Mario Kart 8.
-
B.
Isabelle Allen
Isabelle Allen is a British actress and singer best known for playing young Cosette in the 2012 film adaptation of the musical "Les Misérables."
-
C.
Isabelle Howell
Isabelle Howell was the sister of Dorothy Howell Rodham, making her the maternal aunt of Hillary Rodham Clinton.
-
D.
Isabella Sermon
Isabella Sermon is a British actress best known for playing Maisie Lockwood in the Jurassic World film series.
-
E.
Isabelle Devinck
Isabelle Devinck is a French film editor known for her work on the movie "Cible émouvante."
- 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_69d1cc5b4dd8819088c86946b4eb8a39 |
completed | April 5, 2026, 2:43 a.m. |
Created at: March 30, 2026, 8:30 p.m.