Triple
T9442315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chef Defensie |
E227674
|
entity |
| Predicate | officeHolder |
P537
|
FINISHED |
| Object | Michel Hofman |
E269780
|
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: Michel Hofman | Statement: [Chef Defensie, officeHolder, Michel Hofman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michel Hofman Context triple: [Chef Defensie, officeHolder, Michel Hofman]
-
A.
Michel Hofman
chosen
Michel Hofman is a Belgian military officer who serves as the country's Chief of Defence, the highest-ranking position in the Belgian Armed Forces.
-
B.
Pierre Hohenberg
Pierre Hohenberg was a theoretical physicist best known for co-formulating the Hohenberg–Kohn theorems, which laid the mathematical foundation of modern density functional theory in quantum mechanics.
-
C.
René Le Hénaff
René Le Hénaff was a French film editor and director known for his work on numerous classic French films in the early to mid-20th century.
-
D.
Boris Dilliès
Boris Dilliès is a Belgian politician known for serving as the mayor of the Brussels municipality of Uccle.
-
E.
Michel Harmand
Michel Harmand is an automotive designer best known for his work on the innovative and aerodynamically styled Citroën CX.
- 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_69ca843884488190ad6cbe0153088234 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f300cc88190a793712706295c53 |
completed | April 1, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dbc697388190b384c7ed9e6a65dc |
completed | April 10, 2026, 11:15 a.m. |
Created at: March 30, 2026, 7:50 p.m.