Triple
T16027023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astrid Hofferson |
E388741
|
entity |
| Predicate | homeLocation |
P75
|
FINISHED |
| Object | Berk |
E1189193
|
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: Berk | Statement: [Astrid Hofferson, homeLocation, Berk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berk Context triple: [Astrid Hofferson, homeLocation, Berk]
-
A.
Berk
Berk is a Turkish surname shared by various individuals, including the notable poet İlhan Berk.
-
B.
Berk
chosen
Berk is the remote Viking island village that serves as the primary setting in the How to Train Your Dragon franchise.
-
C.
Berkheim
Berkheim is a small municipality in the district of Biberach in the federal state of Baden-Württemberg in southern Germany.
-
D.
Berns
Berns is the surname of Alison Berns, an American former radio and television personality best known for her long-term marriage to broadcaster Howard Stern.
-
E.
Berch
Berch is the colloquial nickname for the Erlanger Bergkirchweih, a famous annual beer festival held in Erlangen, Germany.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18328707c8190b9a444c78faaaa04 |
completed | April 17, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbcfd39c81909bfddfe95f9ad7d2 |
completed | May 10, 2026, 1:13 a.m. |
Created at: April 10, 2026, 4:56 a.m.