Triple
T14351691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maxine Gray |
E355867
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Vincent Gray
Vincent Gray is an American politician who served as the mayor of Washington, D.C., from 2011 to 2015.
|
E1095278
|
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: Vincent Gray | Statement: [Maxine Gray, child, Vincent Gray]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vincent Gray Context triple: [Maxine Gray, child, Vincent Gray]
-
A.
Vincent Benedict
Vincent Benedict is one of the mismatched twin brothers in the 1988 comedy film "Twins," portrayed as the street-smart, scheming counterpart to Arnold Schwarzenegger’s character.
-
B.
Vincent Franklin
Vincent Franklin is a British character actor known for his work in television comedies and dramas such as "The Thick of It," "Cucumber," and "Bodyguard."
-
C.
Vincent Herbert
Vincent Herbert is an American music producer and songwriter best known for his work with major R&B and pop artists and for founding Streamline Records.
-
D.
Vincent Lane
Vincent Lane is the father of Jane Lane, a character from the animated television series "Daria."
-
E.
Vincent Newman
Vincent Newman is a film producer known for working on a variety of Hollywood movies, including comedies and genre films.
- 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: Vincent Gray Triple: [Maxine Gray, child, Vincent Gray]
Generated description
Vincent Gray is an American politician who served as the mayor of Washington, D.C., from 2011 to 2015.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vincent Gray Target entity description: Vincent Gray is an American politician who served as the mayor of Washington, D.C., from 2011 to 2015.
-
A.
Vincent Benedict
Vincent Benedict is one of the mismatched twin brothers in the 1988 comedy film "Twins," portrayed as the street-smart, scheming counterpart to Arnold Schwarzenegger’s character.
-
B.
Vincent Franklin
Vincent Franklin is a British character actor known for his work in television comedies and dramas such as "The Thick of It," "Cucumber," and "Bodyguard."
-
C.
Vincent Herbert
Vincent Herbert is an American music producer and songwriter best known for his work with major R&B and pop artists and for founding Streamline Records.
-
D.
Vincent Lane
Vincent Lane is the father of Jane Lane, a character from the animated television series "Daria."
-
E.
Vincent Newman
Vincent Newman is a film producer known for working on a variety of Hollywood movies, including comedies and genre films.
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f4e1e588190bdc7aaf7a2819948 |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c4335e481909d4db39b8d25edc9 |
completed | May 8, 2026, 2:36 a.m. |
| NEDg | Description generation | batch_69fd4e795948819097c43e30902f1654 |
completed | May 8, 2026, 2:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd4f04d7ec819095b64d4811440166 |
completed | May 8, 2026, 2:48 a.m. |
Created at: April 10, 2026, 1:14 a.m.