Triple
T12438846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donnie |
E297217
|
entity |
| Predicate | grandfatherInLaw |
P85496
|
FINISHED |
| Object |
Duke Evers
Duke Evers is a man known primarily as the grandfather-in-law of Donnie.
|
E983981
|
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: Duke Evers | Statement: [Donnie, grandfatherInLaw, Duke Evers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duke Evers Context triple: [Donnie, grandfatherInLaw, Duke Evers]
-
A.
Thomas Duke
Thomas Duke is the son of American astronaut and Apollo 16 lunar module pilot Charles M. Duke Jr.
-
B.
Charles Seymour
Charles Seymour was an American historian and academic leader who served as president of Yale University in the mid-20th century.
-
C.
Duke L.J.
Duke L.J. is the standard abbreviation for the Duke Law Journal, a leading scholarly publication of Duke University School of Law.
-
D.
Robert Dukes
Robert Dukes is an author best known for writing the second installment of the "Bound" series.
-
E.
David Dukes
David Dukes was an American character actor known for his extensive work in film, television, and theater from the 1970s through the 1990s.
- 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: Duke Evers Triple: [Donnie, grandfatherInLaw, Duke Evers]
Generated description
Duke Evers is a man known primarily as the grandfather-in-law of Donnie.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Duke Evers Target entity description: Duke Evers is a man known primarily as the grandfather-in-law of Donnie.
-
A.
Thomas Duke
Thomas Duke is the son of American astronaut and Apollo 16 lunar module pilot Charles M. Duke Jr.
-
B.
Charles Seymour
Charles Seymour was an American historian and academic leader who served as president of Yale University in the mid-20th century.
-
C.
Duke L.J.
Duke L.J. is the standard abbreviation for the Duke Law Journal, a leading scholarly publication of Duke University School of Law.
-
D.
Robert Dukes
Robert Dukes is an author best known for writing the second installment of the "Bound" series.
-
E.
David Dukes
David Dukes was an American character actor known for his extensive work in film, television, and theater from the 1970s through the 1990s.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d8dc0f881908a3da736d8947ce1 |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f0911a08190ba84a20950762e68 |
completed | May 2, 2026, 6:14 p.m. |
| NEDg | Description generation | batch_69f640ef7dd08190bf78d04cffac1a44 |
completed | May 2, 2026, 6:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f641abe114819093d99a327f2220c2 |
completed | May 2, 2026, 6:25 p.m. |
Created at: April 8, 2026, 9:55 p.m.