Triple
T23074419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salome Violetta Haertel |
E575288
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Haertel
Haertel is a German-language surname borne by various individuals, including contemporary figures such as Salome Violetta Haertel.
|
E1569104
|
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: Haertel | Statement: [Salome Violetta Haertel, familyName, Haertel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haertel Context triple: [Salome Violetta Haertel, familyName, Haertel]
-
A.
Höttges
Höttges is a German surname most prominently associated with Timotheus Höttges, the CEO of Deutsche Telekom.
-
B.
Holterberg
Holterberg is a prominent hilly nature area in the Netherlands known for its heathlands, forests, and hiking and cycling trails within the Sallandse Heuvelrug National Park.
-
C.
Hechtel
Hechtel is a village in the Belgian municipality of Hechtel-Eksel, located in the province of Limburg.
-
D.
Herting
Herting is a given name associated with Johanna Herting Roebling, likely of Germanic origin and relatively uncommon in contemporary use.
-
E.
Hedebrant
Hedebrant is a Swedish surname most notably borne by actor Kåre Hedebrant, known for his role in the film "Let the Right One In."
- 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: Haertel Triple: [Salome Violetta Haertel, familyName, Haertel]
Generated description
Haertel is a German-language surname borne by various individuals, including contemporary figures such as Salome Violetta Haertel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Haertel Target entity description: Haertel is a German-language surname borne by various individuals, including contemporary figures such as Salome Violetta Haertel.
-
A.
Höttges
Höttges is a German surname most prominently associated with Timotheus Höttges, the CEO of Deutsche Telekom.
-
B.
Holterberg
Holterberg is a prominent hilly nature area in the Netherlands known for its heathlands, forests, and hiking and cycling trails within the Sallandse Heuvelrug National Park.
-
C.
Hechtel
Hechtel is a village in the Belgian municipality of Hechtel-Eksel, located in the province of Limburg.
-
D.
Herting
Herting is a given name associated with Johanna Herting Roebling, likely of Germanic origin and relatively uncommon in contemporary use.
-
E.
Hedebrant
Hedebrant is a Swedish surname most notably borne by actor Kåre Hedebrant, known for his role in the film "Let the Right One In."
- 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c61bb7c8190a3d9b1fba173cdff |
completed | April 29, 2026, 4:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c15aaf74881909d2cd5f3d730f1b4 |
completed | May 19, 2026, 7:47 a.m. |
| NEDg | Description generation | batch_6a0c15f186208190889e0766ddf03343 |
completed | May 19, 2026, 7:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c165b716c8190b1c1e1683fe897db |
completed | May 19, 2026, 7:50 a.m. |
Created at: April 17, 2026, 3:56 p.m.