Triple
T11143425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Märtha of Sweden |
E263613
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Märtha
Märtha was a Swedish princess and Crown Princess of Norway, known for her humanitarian work and influential role during World War II.
|
E907666
|
NE FINISHED |
How this triple was built (4 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: Märtha | Statement: [Princess Märtha of Sweden, givenName, Märtha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Märtha Context triple: [Princess Märtha of Sweden, givenName, Märtha]
-
A.
Margarete
Margarete is a female given name of Greek origin, commonly associated with the meaning "pearl" and used in various European languages.
-
B.
Christa
Christa was the first name of Christa McAuliffe, the American teacher and astronaut selected as the first private citizen to fly in space.
-
C.
Maddalene
Maddalene is a feminine given name, typically considered a variant of Maddalena or Magdalene, with roots in Christian and European naming traditions.
-
D.
Marlen
Marlen is a village district of the town of Kehl in the German state of Baden-Württemberg.
-
E.
Margot Wendice
Margot Wendice is the wealthy wife targeted in her husband's elaborate murder plot in Alfred Hitchcock's thriller "Dial M for Murder."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Märtha Triple: [Princess Märtha of Sweden, givenName, Märtha]
Generated description
Märtha was a Swedish princess and Crown Princess of Norway, known for her humanitarian work and influential role during World War II.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Märtha Target entity description: Märtha was a Swedish princess and Crown Princess of Norway, known for her humanitarian work and influential role during World War II.
-
A.
Margarete
Margarete is a female given name of Greek origin, commonly associated with the meaning "pearl" and used in various European languages.
-
B.
Christa
Christa was the first name of Christa McAuliffe, the American teacher and astronaut selected as the first private citizen to fly in space.
-
C.
Maddalene
Maddalene is a feminine given name, typically considered a variant of Maddalena or Magdalene, with roots in Christian and European naming traditions.
-
D.
Marlen
Marlen is a village district of the town of Kehl in the German state of Baden-Württemberg.
-
E.
Margot Wendice
Margot Wendice is the wealthy wife targeted in her husband's elaborate murder plot in Alfred Hitchcock's thriller "Dial M for Murder."
- F. None of above. chosen
Provenance (5 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_69d6aa9c0ba08190bbd19c217489b755 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8623158819096ad1678fa9e72bb |
completed | April 9, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e44215513481908909ce4289aabca6 |
completed | April 19, 2026, 2:46 a.m. |
| NEDg | Description generation | batch_69e44c09dd5c8190bddf3dd109a639ba |
completed | April 19, 2026, 3:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e451274ce48190a05f1d37f972c36c |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 8, 2026, 9:28 p.m.