Triple
T10648853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madeleine Swann |
E250908
|
entity |
| Predicate | parentOf |
P120
|
FINISHED |
| Object | Mathilde |
E547027
|
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: Mathilde | Statement: [Madeleine Swann, parentOf, Mathilde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mathilde Context triple: [Madeleine Swann, parentOf, Mathilde]
-
A.
Mathilde
Mathilde was a medieval noblewoman, historically noted as a daughter of Bernard I, Duke of Saxony.
-
B.
Mathilde
chosen
Mathilde is a feminine given name of Germanic origin, commonly used in various European countries.
-
C.
Mathilde
"Mathilde" is a dramatic chanson by Belgian singer-songwriter Jacques Brel, known for its intense emotional narrative and theatrical style.
-
D.
Mathilde Marie Christine Ghislaine d’Udekem d’Acoz
Mathilde Marie Christine Ghislaine d’Udekem d’Acoz is the Queen of the Belgians, consort to King Philippe and a prominent member of the Belgian royal family.
-
E.
Mathilde Mauté
Mathilde Mauté was the wife and muse of French poet Paul Verlaine, known primarily through her portrayal in accounts of his tumultuous life and relationships.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfe3ea08819094a945ebb7fc4d3a |
completed | April 8, 2026, 11:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d97a60fdd881908987f920a19bb41e |
completed | April 10, 2026, 10:32 p.m. |
Created at: April 8, 2026, 9:06 p.m.