Triple
T23200251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Associated British Foods |
E579986
|
entity |
| Predicate | owns |
P347
|
FINISHED |
| Object |
Twinings
Twinings is a historic British tea company renowned worldwide for its wide range of premium teas and herbal infusions.
|
E1575435
|
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: Twinings | Statement: [Associated British Foods, owns, Twinings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Twinings Context triple: [Associated British Foods, owns, Twinings]
-
A.
Lipton
Lipton is a globally recognized tea brand offering a wide range of tea products, including black, green, and herbal varieties.
-
B.
Tata Tea
Tata Tea is a major Indian tea brand and beverage company, part of the Tata Group, known for its wide range of packaged teas and strong presence in the domestic and international markets.
-
C.
Teavana
Teavana is a specialty tea retailer and brand known for its loose-leaf teas, tea accessories, and tea-centric beverages.
-
D.
Tunnock's
Tunnock's is a famous Scottish confectionery company best known for its caramel wafers and teacakes.
-
E.
Maxwell House
Maxwell House is a long-standing American coffee brand known for its mass-market ground and instant coffees and the slogan "Good to the last drop."
- 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: Twinings Triple: [Associated British Foods, owns, Twinings]
Generated description
Twinings is a historic British tea company renowned worldwide for its wide range of premium teas and herbal infusions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Twinings Target entity description: Twinings is a historic British tea company renowned worldwide for its wide range of premium teas and herbal infusions.
-
A.
Lipton
Lipton is a globally recognized tea brand offering a wide range of tea products, including black, green, and herbal varieties.
-
B.
Tata Tea
Tata Tea is a major Indian tea brand and beverage company, part of the Tata Group, known for its wide range of packaged teas and strong presence in the domestic and international markets.
-
C.
Teavana
Teavana is a specialty tea retailer and brand known for its loose-leaf teas, tea accessories, and tea-centric beverages.
-
D.
Tunnock's
Tunnock's is a famous Scottish confectionery company best known for its caramel wafers and teacakes.
-
E.
Maxwell House
Maxwell House is a long-standing American coffee brand known for its mass-market ground and instant coffees and the slogan "Good to the last drop."
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f19078f28c8190973f1bd6f2bceb5a |
completed | April 29, 2026, 5 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c30c0ca108190bde7fe9fba83d732 |
completed | May 19, 2026, 9:43 a.m. |
| NEDg | Description generation | batch_6a0c330135cc8190b5a0e512bda6277d |
completed | May 19, 2026, 9:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c375dd5a4819097a80ae43a1c4442 |
completed | May 19, 2026, 10:11 a.m. |
Created at: April 17, 2026, 4:06 p.m.