Triple
T6055399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron Monck of Potheridge |
E134896
|
entity |
| Predicate | nobleFamilyName |
P18
|
FINISHED |
| Object | Monck |
E125765
|
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: Monck | Statement: [Baron Monck of Potheridge, nobleFamilyName, Monck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Monck Context triple: [Baron Monck of Potheridge, nobleFamilyName, Monck]
-
A.
Monck
chosen
Monck is the surname of George Monck, the 17th-century English general instrumental in the Restoration of King Charles II.
-
B.
Marquet
Marquet is a French surname most notably associated with the Fauvist painter Albert Marquet.
-
C.
Piet
Piet is a masculine given name of Dutch origin, commonly used in the Netherlands and Belgium.
-
D.
Theo van Gogh
Theo van Gogh was a Dutch art dealer and the younger brother and close confidant of painter Vincent van Gogh, known for emotionally and financially supporting Vincent and helping promote his work.
-
E.
van Gogh
Van Gogh is a renowned Dutch surname most famously associated with the post-impressionist painter Vincent van Gogh and his family.
- 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_69c00877b6d4819096b0e163728b73a3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0570a863c819090291775245708d6 |
completed | March 22, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c113b06d188190839cfc48a2461d65 |
completed | March 23, 2026, 10:19 a.m. |
Created at: March 22, 2026, 4:09 p.m.