Triple
T9924419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gertrude |
E187883
|
entity |
| Predicate | cognate |
P2527
|
FINISHED |
| Object | Geertruida |
E828908
|
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: Geertruida | Statement: [Gertrude, cognate, Geertruida]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geertruida Context triple: [Gertrude, cognate, Geertruida]
-
A.
Geertruida
chosen
Geertruida is a Dutch feminine given name, corresponding to the English name Gertrude.
-
B.
Neeltje Jans
Neeltje Jans was the wife of famed Dutch admiral Michiel de Ruyter and a 17th-century Dutch woman about whom relatively little is historically documented compared to her prominent husband.
-
C.
Marijke
Marijke is the baptismal name of Princess Christina of the Netherlands, the youngest daughter of Queen Juliana and Prince Bernhard.
-
D.
Hendrika
Hendrika is a feminine given name of Dutch origin, commonly used in the Netherlands and related to the name Hendrickje.
-
E.
Geertje Dircx
Geertje Dircx was a 17th-century Dutch woman known primarily as Rembrandt’s former lover and housekeeper, later believed by some scholars to have modeled for his painting "Danaë."
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb598651081908286763ff56ba57c |
completed | April 2, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228c23a2c81908fa2cb3a4f90d198 |
completed | April 5, 2026, 9:17 a.m. |
Created at: March 30, 2026, 8:43 p.m.