Triple
T15993745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tate & Lyle |
E387904
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object |
T&L
T&L is the common abbreviation for Tate & Lyle, a British multinational agribusiness and food ingredients company best known for producing sweeteners and other specialty food ingredients.
|
E1188461
|
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: T&L | Statement: [Tate & Lyle, hasAbbreviation, T&L]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T&L Context triple: [Tate & Lyle, hasAbbreviation, T&L]
-
A.
TLT
TLT is the IATA airport code for the small public airport serving the remote community of Tuluksak in western Alaska.
-
B.
TLT
TLT is the time zone abbreviation used for Timor Leste Time, the standard time observed in East Timor.
-
C.
TLL
TLL is the three-letter IATA airport code for Lennart Meri Tallinn Airport, the main international airport serving Tallinn, Estonia.
-
D.
TLW
TLW is the Polish vehicle registration code assigned to cars registered in the town of Włoszczowa.
-
E.
TLA
TLA is a formal specification language developed by Leslie Lamport for describing and reasoning about concurrent and distributed systems using temporal logic.
- 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: T&L Triple: [Tate & Lyle, hasAbbreviation, T&L]
Generated description
T&L is the common abbreviation for Tate & Lyle, a British multinational agribusiness and food ingredients company best known for producing sweeteners and other specialty food ingredients.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: T&L Target entity description: T&L is the common abbreviation for Tate & Lyle, a British multinational agribusiness and food ingredients company best known for producing sweeteners and other specialty food ingredients.
-
A.
TLT
TLT is the time zone abbreviation used for Timor Leste Time, the standard time observed in East Timor.
-
B.
TLT
TLT is the IATA airport code for the small public airport serving the remote community of Tuluksak in western Alaska.
-
C.
TLL
TLL is the three-letter IATA airport code for Lennart Meri Tallinn Airport, the main international airport serving Tallinn, Estonia.
-
D.
TLW
TLW is the Polish vehicle registration code assigned to cars registered in the town of Włoszczowa.
-
E.
TLA
TLA is a formal specification language developed by Leslie Lamport for describing and reasoning about concurrent and distributed systems using temporal logic.
- 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_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_69ffc3d5d72081908aa235c5ad9b5707 |
completed | May 9, 2026, 11:31 p.m. |
| NEDg | Description generation | batch_69ffc5444c1c8190854de5575b9ec1c5 |
completed | May 9, 2026, 11:37 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffc5b95290819098b28c44c22b2799 |
completed | May 9, 2026, 11:39 p.m. |
Created at: April 10, 2026, 4:55 a.m.