Triple
T9096538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barry Robinson |
E218036
|
entity |
| Predicate | friendOf |
P8712
|
FINISHED |
| Object | Snot Lonstein |
E161230
|
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: Snot Lonstein | Statement: [Barry Robinson, friendOf, Snot Lonstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snot Lonstein Context triple: [Barry Robinson, friendOf, Snot Lonstein]
-
A.
Snot Lonstein
chosen
Snot Lonstein is a fictional character from the animated TV series "American Dad!", known as one of Steve Smith's nerdy best friends.
-
B.
Wallot
Wallot is a German surname most notably associated with architect Paul Wallot, designer of the Reichstag building in Berlin.
-
C.
Lontzen
Lontzen is a municipality in eastern Belgium, located in the country’s German-speaking region near the border with Germany.
-
D.
Els Borst
Els Borst was a Dutch politician and physician best known for serving as Minister of Health and for her leading role in legalizing euthanasia in the Netherlands.
-
E.
Lennertz
Lennertz is a German-origin surname borne by various individuals, including American composer Christopher Lennertz.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc96b7d0d48190a3b15f35bef087e3 |
completed | April 1, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0181a9ae88190ab80d4e80e919f42 |
completed | April 3, 2026, 7:42 p.m. |
Created at: March 30, 2026, 7:15 p.m.