Triple
T15993720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tate & Lyle |
E387904
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Abram Lyle |
E1188454
|
NE FINISHED |
How this triple was built (2 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: Abram Lyle | Statement: [Tate & Lyle, foundedBy, Abram Lyle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abram Lyle Context triple: [Tate & Lyle, foundedBy, Abram Lyle]
-
A.
Abram Lyle
chosen
Abram Lyle was a 19th-century Scottish sugar refiner and industrialist best known for founding the company that created the iconic Lyle’s Golden Syrup.
-
B.
Abraham Anderson
Abraham Anderson was an American businessman best known as a co-founder of the Campbell Soup Company.
-
C.
Abraham Hart
Abraham Hart was a 19th-century American publisher best known as the co-founder of the influential Philadelphia publishing firm Carey and Hart.
-
D.
John Nelson Abrams
John Nelson Abrams is the son of U.S. Army General Creighton Abrams, who served as Army Chief of Staff and commanded U.S. forces in Vietnam.
-
E.
Abraham Wells
Abraham Wells was an individual significant enough in local history that the village of Wellsburg, New York, was named in his honor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e15785347081908831b4cbc9a2dd45 |
completed | April 16, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf1cb1388190b1ebccc6705e5974 |
completed | May 10, 2026, 12:19 a.m. |
Created at: April 10, 2026, 4:55 a.m.