Triple
T4438829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alston & Bird |
E95717
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Guyton Alston
Guyton Alston was a key founding figure behind the prominent U.S. law firm Alston & Bird.
|
E449731
|
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: Guyton Alston | Statement: [Alston & Bird, foundedBy, Guyton Alston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Guyton Alston Context triple: [Alston & Bird, foundedBy, Guyton Alston]
-
A.
Eric E. Osmond
Eric E. Osmond is a film editor best known for his work on the animated feature "The Super Mario Bros. Movie."
-
B.
William Howell Davis
William Howell Davis was the son of Varina Howell Davis and Confederate President Jefferson Davis, belonging to a prominent family in American Civil War history.
-
C.
Charles Alton Ellis
Charles Alton Ellis was an American structural engineer best known for performing the complex mathematical and design work that made the Golden Gate Bridge possible.
-
D.
Samuel Lane Loomis
Samuel Lane Loomis was an American Congregational minister, educator, and author active in the late 19th and early 20th centuries.
-
E.
Fred M. Wilcox
Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
- 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: Guyton Alston Triple: [Alston & Bird, foundedBy, Guyton Alston]
Generated description
Guyton Alston was a key founding figure behind the prominent U.S. law firm Alston & Bird.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Guyton Alston Target entity description: Guyton Alston was a key founding figure behind the prominent U.S. law firm Alston & Bird.
-
A.
Eric E. Osmond
Eric E. Osmond is a film editor best known for his work on the animated feature "The Super Mario Bros. Movie."
-
B.
William Howell Davis
William Howell Davis was the son of Varina Howell Davis and Confederate President Jefferson Davis, belonging to a prominent family in American Civil War history.
-
C.
Charles Alton Ellis
Charles Alton Ellis was an American structural engineer best known for performing the complex mathematical and design work that made the Golden Gate Bridge possible.
-
D.
Samuel Lane Loomis
Samuel Lane Loomis was an American Congregational minister, educator, and author active in the late 19th and early 20th centuries.
-
E.
Fred M. Wilcox
Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
- 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_69b3453ea2b48190a26f154b3b8fece5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355aaa9288190b95d875d343d6ee5 |
completed | March 13, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bda41426ec8190a239da38bd3643fd |
completed | March 20, 2026, 7:46 p.m. |
| NEDg | Description generation | batch_69bda5e9ccc48190bfde05c935db0ef6 |
completed | March 20, 2026, 7:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bda635f8d8819095604fdeab5e39e7 |
completed | March 20, 2026, 7:55 p.m. |
Created at: March 12, 2026, 11:31 p.m.