Triple
T16699996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treves |
E405818
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object |
Wolfram Leibe
Wolfram Leibe is a German politician who serves as the mayor of the city of Trier.
|
E1231732
|
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: Wolfram Leibe | Statement: [Treves, hasMayor, Wolfram Leibe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wolfram Leibe Context triple: [Treves, hasMayor, Wolfram Leibe]
-
A.
Wolfram Sievers
Wolfram Sievers was a Nazi SS officer and managing director of the Ahnenerbe who was convicted and executed for war crimes and crimes against humanity for his role in human experimentation during World War II.
-
B.
Marten Wassmann
Marten Wassmann is an architect known for his partnership role at the Dutch architecture firm Benthem Crouwel Architekten.
-
C.
Martin Weil
Martin Weil is a journalist and writer best known for his long career as a reporter and editor at The Washington Post.
-
D.
Thomas Römer
Thomas Römer is a prominent French biblical scholar and historian of ancient Israel, known for his influential work on the composition and historical context of the Hebrew Bible.
-
E.
Sebastian Bodenstein
Sebastian Bodenstein is a researcher who contributed as a co-author to the landmark 2021 Nature paper by Jumper et al. describing the AlphaFold protein structure prediction system.
- 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: Wolfram Leibe Triple: [Treves, hasMayor, Wolfram Leibe]
Generated description
Wolfram Leibe is a German politician who serves as the mayor of the city of Trier.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wolfram Leibe Target entity description: Wolfram Leibe is a German politician who serves as the mayor of the city of Trier.
-
A.
Wolfram Sievers
Wolfram Sievers was a Nazi SS officer and managing director of the Ahnenerbe who was convicted and executed for war crimes and crimes against humanity for his role in human experimentation during World War II.
-
B.
Marten Wassmann
Marten Wassmann is an architect known for his partnership role at the Dutch architecture firm Benthem Crouwel Architekten.
-
C.
Martin Weil
Martin Weil is a journalist and writer best known for his long career as a reporter and editor at The Washington Post.
-
D.
Thomas Römer
Thomas Römer is a prominent French biblical scholar and historian of ancient Israel, known for his influential work on the composition and historical context of the Hebrew Bible.
-
E.
Sebastian Bodenstein
Sebastian Bodenstein is a researcher who contributed as a co-author to the landmark 2021 Nature paper by Jumper et al. describing the AlphaFold protein structure prediction system.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e383300d108190911e3cba8e07f2dd |
completed | April 18, 2026, 1:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a51378788190b9f3bb0a344dcdd8 |
completed | May 10, 2026, 3:32 p.m. |
| NEDg | Description generation | batch_6a00a5b3ce848190a73f06d9708bfc85 |
completed | May 10, 2026, 3:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00a6734d008190bb0a5aa28826e73a |
completed | May 10, 2026, 3:38 p.m. |
Created at: April 10, 2026, 5:19 a.m.