Triple
T19818481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Axel von Fersen the Elder |
E476122
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Axel |
—
|
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: Axel | Statement: [Axel von Fersen the Elder, givenName, Axel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Axel Context triple: [Axel von Fersen the Elder, givenName, Axel]
-
A.
Axel
chosen
Axel is a given name associated with the Finnish painter Akseli Gallen-Kallela, renowned for his depictions of the Kalevala and contributions to Finnish national romantic art.
-
B.
Axel
Axel is a child associated with Nairobi, a character from the Spanish television series "Money Heist" (La Casa de Papel).
-
C.
Axel
Axel is a town in the Dutch province of Zeeland, known historically as a fortified settlement and now part of the municipality of Terneuzen.
-
D.
Axel
Axel is a main character in Minecraft: Story Mode, known as a loyal but impulsive member of Jesse’s group who often provides comic relief and brute strength.
-
E.
Axel Young
Axel Young is a pseudonym used by American author Michael McDowell, known for his horror and suspense fiction.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e654fc8b94819095fd5240f33b6713 |
completed | April 20, 2026, 4:31 p.m. |
Created at: April 10, 2026, 1:50 p.m.