Triple
T7650980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allvar Gullstrand |
E173249
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Gullstrand |
E173249
|
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: Gullstrand | Statement: [Allvar Gullstrand, familyName, Gullstrand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gullstrand Context triple: [Allvar Gullstrand, familyName, Gullstrand]
-
A.
Ornea
Ornea is a minor figure in Greek mythology known primarily as one of the many children of the river god Asopus.
-
B.
Allvar Gullstrand
chosen
Allvar Gullstrand was a Swedish ophthalmologist and physicist who won the 1911 Nobel Prize in Physiology or Medicine for his work on the optics of the eye.
-
C.
Ehrenstein
Ehrenstein is a locality or district that forms part of the municipality of Blaustein in the state of Baden-Württemberg, Germany.
-
D.
Köhler
Köhler is a German surname most notably associated with psychologist Wolfgang Köhler, a key figure in the development of Gestalt psychology.
-
E.
Kalmus
Kalmus is a surname most notably associated with Herbert Kalmus, the co-founder of the pioneering color motion picture company Technicolor.
- 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_69c6995473348190a4f41d110d619a18 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70175e4b88190bc40c839a42180d4 |
completed | March 27, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c89ae293148190a30ef03a4a594fe6 |
completed | March 29, 2026, 3:22 a.m. |
Created at: March 27, 2026, 3:58 p.m.