Triple
T16079800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theodor Fontane |
E390074
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object |
Louis Henri Fontane
Louis Henri Fontane was the father of the renowned German novelist and poet Theodor Fontane.
|
E1193051
|
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: Louis Henri Fontane | Statement: [Theodor Fontane, father, Louis Henri Fontane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louis Henri Fontane Context triple: [Theodor Fontane, father, Louis Henri Fontane]
-
A.
Louis Allibert
Louis Allibert was a French actor best known for his role in René Clair’s classic 1931 musical comedy film "Le Million."
-
B.
Paul Landowski
Paul Landowski was a French sculptor best known for designing the monumental statue of Christ the Redeemer overlooking Rio de Janeiro.
-
C.
Armand Jammot
Armand Jammot was a French television producer and director best known for creating influential game and quiz shows.
-
D.
Louis Gohier
Louis Gohier was a French lawyer and politician who served as a member of the French Directory during the late stages of the French Revolution.
-
E.
Pierre-François-Léonard Fontaine
Pierre-François-Léonard Fontaine was a prominent French neoclassical architect and designer, best known for his collaborations with Charles Percier that shaped the Empire style during the Napoleonic era.
- 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: Louis Henri Fontane Triple: [Theodor Fontane, father, Louis Henri Fontane]
Generated description
Louis Henri Fontane was the father of the renowned German novelist and poet Theodor Fontane.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Louis Henri Fontane Target entity description: Louis Henri Fontane was the father of the renowned German novelist and poet Theodor Fontane.
-
A.
Louis Allibert
Louis Allibert was a French actor best known for his role in René Clair’s classic 1931 musical comedy film "Le Million."
-
B.
Paul Landowski
Paul Landowski was a French sculptor best known for designing the monumental statue of Christ the Redeemer overlooking Rio de Janeiro.
-
C.
Armand Jammot
Armand Jammot was a French television producer and director best known for creating influential game and quiz shows.
-
D.
Louis Gohier
Louis Gohier was a French lawyer and politician who served as a member of the French Directory during the late stages of the French Revolution.
-
E.
Pierre-François-Léonard Fontaine
Pierre-François-Léonard Fontaine was a prominent French neoclassical architect and designer, best known for his collaborations with Charles Percier that shaped the Empire style during the Napoleonic era.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18448bebc8190b0e84b1da097bf8b |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe48adec081909623355eabee472c |
completed | May 10, 2026, 1:51 a.m. |
| NEDg | Description generation | batch_69ffe6af1c4081908b57f4dc485fbb14 |
completed | May 10, 2026, 2 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffe769d56081908f723e92d327e315 |
completed | May 10, 2026, 2:03 a.m. |
Created at: April 10, 2026, 4:57 a.m.