Triple
T22791088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Ridenhour Courage Prize |
E564110
|
entity |
| Predicate | hasAwarded |
P2391
|
FINISHED |
| Object |
Matthew Hoh
Matthew Hoh is a former U.S. Marine and State Department official known for his principled resignation over the Afghanistan War and subsequent antiwar activism.
|
E1554669
|
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: Matthew Hoh | Statement: [Ron Ridenhour Courage Prize, hasAwarded, Matthew Hoh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Hoh Context triple: [Ron Ridenhour Courage Prize, hasAwarded, Matthew Hoh]
-
A.
Brian Teta
Brian Teta is a television producer best known for serving as the executive producer of the daytime talk show "The View."
-
B.
Matthew Nathanson
Matthew Nathanson is a singer-songwriter known for his melodic, introspective pop-rock music and emotionally resonant lyrics.
-
C.
Steven Fanning
Steven Fanning is the father of American actresses Dakota and Elle Fanning and a former minor league baseball player.
-
D.
Matthew Freund
Matthew Freund is a film editor known for his work on the comedy movie "Fist Fight."
-
E.
Jon Oberheide
Jon Oberheide is a cybersecurity entrepreneur and researcher best known as the co-founder and former CTO of Duo Security, a leading multi-factor authentication and zero-trust security company.
- 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: Matthew Hoh Triple: [Ron Ridenhour Courage Prize, hasAwarded, Matthew Hoh]
Generated description
Matthew Hoh is a former U.S. Marine and State Department official known for his principled resignation over the Afghanistan War and subsequent antiwar activism.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matthew Hoh Target entity description: Matthew Hoh is a former U.S. Marine and State Department official known for his principled resignation over the Afghanistan War and subsequent antiwar activism.
-
A.
Brian Teta
Brian Teta is a television producer best known for serving as the executive producer of the daytime talk show "The View."
-
B.
Matthew Nathanson
Matthew Nathanson is a singer-songwriter known for his melodic, introspective pop-rock music and emotionally resonant lyrics.
-
C.
Steven Fanning
Steven Fanning is the father of American actresses Dakota and Elle Fanning and a former minor league baseball player.
-
D.
Matthew Freund
Matthew Freund is a film editor known for his work on the comedy movie "Fist Fight."
-
E.
Jon Oberheide
Jon Oberheide is a cybersecurity entrepreneur and researcher best known as the co-founder and former CTO of Duo Security, a leading multi-factor authentication and zero-trust security company.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c3545fc819084af67cc25e94839 |
completed | April 29, 2026, 3:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b9e905b148190b319d88ca3e7ca8e |
completed | May 18, 2026, 11:19 p.m. |
| NEDg | Description generation | batch_6a0b9f0e73048190ac2e1ad53912dde5 |
completed | May 18, 2026, 11:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b9ff292b88190b1f318a8a801fbd1 |
completed | May 18, 2026, 11:25 p.m. |
Created at: April 17, 2026, 3:30 p.m.