Triple

T22291878
Position Surface form Disambiguated ID Type / Status
Subject Jolie Gabor E551017 entity
Predicate birthName P65 FINISHED
Object Janka Tilleman
Janka Tilleman was the Hungarian-born woman who later became known as Jolie Gabor, a prominent socialite and the mother of actresses Zsa Zsa, Eva, and Magda Gabor.
 E1531650 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: Janka Tilleman | Statement: [Jolie Gabor, birthName, Janka Tilleman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Janka Tilleman
Context triple: [Jolie Gabor, birthName, Janka Tilleman]
  • A. Thekla Reuten
    Thekla Reuten is a Dutch actress known for her roles in international films and television series, including English-language productions.
  • B. Martje Grohmann
    Martje Grohmann is a German photographer and former wife of renowned filmmaker Werner Herzog.
  • C. Johanna Geilus
    Johanna Geilus was the wife of Austrian journalist and politician Fritz Austerlitz.
  • D. Johanna Mylius
    Johanna Mylius was a noblewoman known primarily as the wife of Václav Eusebius, Prince of Lobkowicz, a prominent 17th-century Bohemian statesman and aristocrat.
  • E. Janine Elschot
    Janine Elschot is a long-running central character in the Dutch soap opera "Goede tijden, slechte tijden," known for her dramatic personal and professional storylines.
  • 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: Janka Tilleman
Triple: [Jolie Gabor, birthName, Janka Tilleman]
Generated description
Janka Tilleman was the Hungarian-born woman who later became known as Jolie Gabor, a prominent socialite and the mother of actresses Zsa Zsa, Eva, and Magda Gabor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Janka Tilleman
Target entity description: Janka Tilleman was the Hungarian-born woman who later became known as Jolie Gabor, a prominent socialite and the mother of actresses Zsa Zsa, Eva, and Magda Gabor.
  • A. Thekla Reuten
    Thekla Reuten is a Dutch actress known for her roles in international films and television series, including English-language productions.
  • B. Martje Grohmann
    Martje Grohmann is a German photographer and former wife of renowned filmmaker Werner Herzog.
  • C. Johanna Geilus
    Johanna Geilus was the wife of Austrian journalist and politician Fritz Austerlitz.
  • D. Johanna Mylius
    Johanna Mylius was a noblewoman known primarily as the wife of Václav Eusebius, Prince of Lobkowicz, a prominent 17th-century Bohemian statesman and aristocrat.
  • E. Janine Elschot
    Janine Elschot is a long-running central character in the Dutch soap opera "Goede tijden, slechte tijden," known for her dramatic personal and professional storylines.
  • 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_69e11e45fb848190a1b2ae21296e3a5f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1560d1ec48190ab86f158c94b677b completed April 29, 2026, 12:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ad5106fc881908929055c7ce314e0 completed May 18, 2026, 9 a.m.
NEDg Description generation batch_6a0ad991a1e48190ad240a20694223fc completed May 18, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0ada2a61b881908a636b2d1d6e4509 completed May 18, 2026, 9:21 a.m.
Created at: April 16, 2026, 8:41 p.m.