Triple
T22778610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Dekker |
E563772
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object |
Samuel Thomas Dekker
Samuel Thomas Dekker is an American professional basketball player known for his collegiate career at the University of Wisconsin and subsequent play in the NBA and overseas leagues.
|
E1554970
|
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: Samuel Thomas Dekker | Statement: [Sam Dekker, fullName, Samuel Thomas Dekker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samuel Thomas Dekker Context triple: [Sam Dekker, fullName, Samuel Thomas Dekker]
-
A.
Scott Decker
Scott Decker is a member of the visual effects and animation company Trixter, contributing to its film and media projects.
-
B.
Steve Dekorte
Steve Dekorte is a software developer best known as the creator of the prototype-based Io programming language.
-
C.
Dirk DeJong
Dirk DeJong is the ambitious son of a Dutch-American widow whose moral and personal development forms the central focus of Edna Ferber’s novel "So Big."
-
D.
Ben Dunkelman
Ben Dunkelman was a Canadian-born Jewish officer and businessman best known for his prominent command role in Israel’s 1948 War of Independence.
-
E.
De Decker
De Decker is a Belgian surname most notably associated with politician Armand De Decker.
- 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: Samuel Thomas Dekker Triple: [Sam Dekker, fullName, Samuel Thomas Dekker]
Generated description
Samuel Thomas Dekker is an American professional basketball player known for his collegiate career at the University of Wisconsin and subsequent play in the NBA and overseas leagues.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Samuel Thomas Dekker Target entity description: Samuel Thomas Dekker is an American professional basketball player known for his collegiate career at the University of Wisconsin and subsequent play in the NBA and overseas leagues.
-
A.
Scott Decker
Scott Decker is a member of the visual effects and animation company Trixter, contributing to its film and media projects.
-
B.
Steve Dekorte
Steve Dekorte is a software developer best known as the creator of the prototype-based Io programming language.
-
C.
Dirk DeJong
Dirk DeJong is the ambitious son of a Dutch-American widow whose moral and personal development forms the central focus of Edna Ferber’s novel "So Big."
-
D.
Ben Dunkelman
Ben Dunkelman was a Canadian-born Jewish officer and businessman best known for his prominent command role in Israel’s 1948 War of Independence.
-
E.
De Decker
De Decker is a Belgian surname most notably associated with politician Armand De Decker.
- 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_69e24554497c819080b996e071de27c2 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17b631c6881908a6687920923dcf4 |
completed | April 29, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b9e8c5aac8190b3c9d22676205c8e |
completed | May 18, 2026, 11:19 p.m. |
| NEDg | Description generation | batch_6a0b9f73032481908f0df881801de5b2 |
completed | May 18, 2026, 11:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ba068def08190b22058cf5bd76b4f |
completed | May 18, 2026, 11:27 p.m. |
Created at: April 17, 2026, 3:28 p.m.