Triple
T7336777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Colson |
E169146
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Colson
Colson is a surname most notably associated with Charles Colson, the American political aide involved in the Watergate scandal who later became an evangelical Christian leader and author.
|
E657874
|
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: Colson | Statement: [Charles Colson, familyName, Colson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Colson Context triple: [Charles Colson, familyName, Colson]
-
A.
Osborne Colson
Osborne Colson was a prominent Canadian figure skating coach and former national champion known for mentoring several elite skaters.
-
B.
Calvin Wheeler
Calvin Wheeler is a fictional character portrayed by actor Lee Thompson Young, best known from his work in film and television.
-
C.
Josh Coalson
Josh Coalson is a software developer best known as the creator and original author of the FLAC (Free Lossless Audio Codec) audio compression format.
-
D.
Vance
Vance is a surname most prominently associated with Emmy and Tony Award–winning American actor Courtney B. Vance.
-
E.
Corwin
Corwin is a surname most notably associated with Jonathan Corwin, a judge involved in the Salem witch trials in 17th-century Massachusetts.
- 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: Colson Triple: [Charles Colson, familyName, Colson]
Generated description
Colson is a surname most notably associated with Charles Colson, the American political aide involved in the Watergate scandal who later became an evangelical Christian leader and author.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Colson Target entity description: Colson is a surname most notably associated with Charles Colson, the American political aide involved in the Watergate scandal who later became an evangelical Christian leader and author.
-
A.
Osborne Colson
Osborne Colson was a prominent Canadian figure skating coach and former national champion known for mentoring several elite skaters.
-
B.
Calvin Wheeler
Calvin Wheeler is a fictional character portrayed by actor Lee Thompson Young, best known from his work in film and television.
-
C.
Josh Coalson
Josh Coalson is a software developer best known as the creator and original author of the FLAC (Free Lossless Audio Codec) audio compression format.
-
D.
Vance
Vance is a surname most prominently associated with Emmy and Tony Award–winning American actor Courtney B. Vance.
-
E.
Corwin
Corwin is a surname most notably associated with Jonathan Corwin, a judge involved in the Salem witch trials in 17th-century Massachusetts.
- 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_69c68a568a6481908f11e20db7bc8446 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0c51884819098fe00dd3d5e44b2 |
completed | March 27, 2026, 9:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ef22d6ac819087f05d6e6787509a |
completed | March 28, 2026, 3:09 p.m. |
| NEDg | Description generation | batch_69c7f58ddcf88190bfc15f673083c009 |
completed | March 28, 2026, 3:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7f615d6d48190933ac515874299b9 |
completed | March 28, 2026, 3:39 p.m. |
Created at: March 27, 2026, 3:04 p.m.