Triple
T4038136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Steenbock |
E83876
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Steenbock
Steenbock is a German-origin surname most notably associated with biochemist Harry Steenbock, known for his pioneering work on vitamin D fortification.
|
E408359
|
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: Steenbock | Statement: [Harry Steenbock, familyName, Steenbock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steenbock Context triple: [Harry Steenbock, familyName, Steenbock]
-
A.
Denshaw
Denshaw is a small rural village in the civil parish of Saddleworth, within the Metropolitan Borough of Oldham in Greater Manchester, England.
-
B.
Nisenan
The Nisenan are an Indigenous people of Northern California, traditionally inhabiting the Sierra Nevada foothills and Sacramento Valley, with a distinct Maidu language and culture.
-
C.
Lauter
Lauter is a small river in Germany that serves as a tributary of the Innerste.
-
D.
Bergensten
Bergensten is the surname of Jens Bergensten, the Swedish video game programmer and lead developer known for his work on Minecraft.
-
E.
Finklea
Finklea is the birth surname of American actress and dancer Cyd Charisse, known for her roles in classic Hollywood musicals.
- 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: Steenbock Triple: [Harry Steenbock, familyName, Steenbock]
Generated description
Steenbock is a German-origin surname most notably associated with biochemist Harry Steenbock, known for his pioneering work on vitamin D fortification.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Steenbock Target entity description: Steenbock is a German-origin surname most notably associated with biochemist Harry Steenbock, known for his pioneering work on vitamin D fortification.
-
A.
Denshaw
Denshaw is a small rural village in the civil parish of Saddleworth, within the Metropolitan Borough of Oldham in Greater Manchester, England.
-
B.
Nisenan
The Nisenan are an Indigenous people of Northern California, traditionally inhabiting the Sierra Nevada foothills and Sacramento Valley, with a distinct Maidu language and culture.
-
C.
Lauter
Lauter is a small river in Germany that serves as a tributary of the Innerste.
-
D.
Bergensten
Bergensten is the surname of Jens Bergensten, the Swedish video game programmer and lead developer known for his work on Minecraft.
-
E.
Finklea
Finklea is the birth surname of American actress and dancer Cyd Charisse, known for her roles in classic Hollywood musicals.
- 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_69aed92f7cf0819098e0539bdcc3767f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb3656f08190aa5286d951013646 |
completed | March 9, 2026, 4:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b55646e5d881909eadd0640a4f1796 |
completed | March 14, 2026, 12:36 p.m. |
| NEDg | Description generation | batch_69b556fec4708190b221893ec35f1a38 |
completed | March 14, 2026, 12:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b557f73cbc8190b904089ab0fa97d6 |
completed | March 14, 2026, 12:43 p.m. |
Created at: March 9, 2026, 3:37 p.m.