Triple
T16280455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Cemetery, Haga |
E395248
|
entity |
| Predicate | hasGraveOf |
P196
|
FINISHED |
| Object | Tord Magnuson |
E944124
|
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: Tord Magnuson | Statement: [Royal Cemetery, Haga, hasGraveOf, Tord Magnuson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tord Magnuson Context triple: [Royal Cemetery, Haga, hasGraveOf, Tord Magnuson]
-
A.
Tord Magnuson
chosen
Tord Magnuson is a Swedish businessman and nobleman best known as the husband of Princess Christina of Sweden.
-
B.
Oscar Lindquist
Oscar Lindquist is a shy, neurotic tax accountant who becomes the love interest of the title character in the musical "Sweet Charity."
-
C.
Oscar Mathisen
Oscar Mathisen was a legendary Norwegian speed skater from the early 20th century, renowned for multiple world records and world titles that made him one of the sport’s greatest figures.
-
D.
Nels Gudmundsson
Nels Gudmundsson is a seasoned, sharp-witted defense attorney in *Snow Falling on Cedars* who plays a key role in uncovering the truth during a contentious murder trial.
-
E.
Nils Erickson
Nils Erickson is a member of the RTX group or organization, likely contributing in a professional or collaborative capacity.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24611926c81909b276ca3f406f15d |
completed | April 17, 2026, 2:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017c48e5c8190a387a4158362417a |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:05 a.m.