Triple
T17223998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matilda of Holstein |
E418062
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Richeza of Sweden |
E1032157
|
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: Richeza of Sweden | Statement: [Matilda of Holstein, child, Richeza of Sweden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richeza of Sweden Context triple: [Matilda of Holstein, child, Richeza of Sweden]
-
A.
Richeza of Sweden
chosen
Richeza of Sweden was a medieval Swedish princess who became Queen consort of Poland through her marriage to King Przemysł II.
-
B.
Richeza of Denmark
Richeza of Denmark was a 13th-century Danish princess who became Queen consort of Sweden through her marriage to King Eric X.
-
C.
Richeza of Poland
Richeza of Poland was a Polish princess of the Piast dynasty who became Queen consort of Hungary and the mother of King Ladislaus I.
-
D.
The Chess Players
The Chess Players is a painting by Irish artist William Orpen, depicting figures absorbed in a game of chess with his characteristic realism and psychological insight.
-
E.
Kráľová dam
Kráľová dam is a major hydroelectric and water-management reservoir on the Váh River in Slovakia, used for power generation, flood control, and irrigation.
- 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42ddfe3bc8190b22cee4fc0590b74 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0167596ab481909df59ce68c7f640e |
completed | May 11, 2026, 5:21 a.m. |
Created at: April 10, 2026, 5:38 a.m.