Triple
T3037244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercedes Jellinek |
E83040
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Mercédès
Mercédès is the given name of Mercédès Jellinek, the woman after whom the Mercedes automobile brand was named.
|
E320408
|
NE FINISHED |
How this triple was built (4 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: Mercédès | Statement: [Mercedes Jellinek, givenName, Mercédès]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mercédès Context triple: [Mercedes Jellinek, givenName, Mercédès]
-
A.
L’Auto
L’Auto was a French sports newspaper best known for creating and organizing the Tour de France.
-
B.
Bindo Maserati
Bindo Maserati was an Italian automotive engineer and one of the Maserati brothers who co-founded the Maserati sports car and racing marque.
-
C.
La Coupée
La Coupée is a dramatic, narrow isthmus with steep cliffs and a coastal road that forms the striking land bridge between the main island of Sark and Little Sark in the Channel Islands.
-
D.
Maybach
Maybach is a historic German luxury automobile and engine brand renowned for its high-end engineering and association with elite, chauffeur-driven cars.
-
E.
Maserati Grecale
The Maserati Grecale is a compact luxury SUV that combines Italian styling with high performance and advanced technology, positioned below the Levante in Maserati’s lineup.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mercédès Triple: [Mercedes Jellinek, givenName, Mercédès]
Generated description
Mercédès is the given name of Mercédès Jellinek, the woman after whom the Mercedes automobile brand was named.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mercédès Target entity description: Mercédès is the given name of Mercédès Jellinek, the woman after whom the Mercedes automobile brand was named.
-
A.
L’Auto
L’Auto was a French sports newspaper best known for creating and organizing the Tour de France.
-
B.
Bindo Maserati
Bindo Maserati was an Italian automotive engineer and one of the Maserati brothers who co-founded the Maserati sports car and racing marque.
-
C.
La Coupée
La Coupée is a dramatic, narrow isthmus with steep cliffs and a coastal road that forms the striking land bridge between the main island of Sark and Little Sark in the Channel Islands.
-
D.
Maybach
Maybach is a historic German luxury automobile and engine brand renowned for its high-end engineering and association with elite, chauffeur-driven cars.
-
E.
Maserati Grecale
The Maserati Grecale is a compact luxury SUV that combines Italian styling with high performance and advanced technology, positioned below the Levante in Maserati’s lineup.
- F. None of above. chosen
Provenance (5 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_69ad8b2298908190a7cb4e9bdbf064d0 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b2cd4988190b52fe3616ecbe9ef |
completed | March 8, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1dec8778c8190a5e06a29a0218404 |
completed | March 11, 2026, 9:29 p.m. |
| NEDg | Description generation | batch_69b1e2c4aaa88190bb5e39c51d0583f0 |
completed | March 11, 2026, 9:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1e3228f488190b13c948c6c5d13d0 |
completed | March 11, 2026, 9:48 p.m. |
Created at: March 8, 2026, 3:01 p.m.