Triple
T20168998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Adelgunde of Bavaria |
E491904
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Adelgunde |
—
|
NE NERFINISHED |
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: Adelgunde | Statement: [Princess Adelgunde of Bavaria, givenName, Adelgunde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adelgunde Context triple: [Princess Adelgunde of Bavaria, givenName, Adelgunde]
-
A.
Adelgunde
chosen
Adelgunde was a Bavarian princess from the royal House of Wittelsbach in the 19th century.
-
B.
Guinedilda of Empúries
Guinedilda of Empúries was a medieval Catalan noblewoman best known as the wife of Wilfred the Hairy, Count of Barcelona, and a member of the influential comital families of northeastern Iberia.
-
C.
Hunilda
Hunilda was a medieval noblewoman known primarily as one of the wives of Bolesław I the Brave, the first crowned king of Poland.
-
D.
Adalinda
Adalinda was a medieval noblewoman known primarily as the wife of William I, Duke of Aquitaine.
-
E.
Ysabell
Ysabell is a character from Terry Pratchett's Discworld series, notably the adopted daughter of Death who appears prominently in the novel "Mort."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66846f4ec81908b0dc6a6e0ec27dd |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.