Triple
T23200260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Associated British Foods |
E579986
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object | AB Mauri |
—
|
NE NERFINISHED |
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: AB Mauri | Statement: [Associated British Foods, subsidiary, AB Mauri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AB Mauri Context triple: [Associated British Foods, subsidiary, AB Mauri]
-
A.
AB Mauri
chosen
AB Mauri is a global business specializing in yeast and bakery ingredients, supplying products and technical support to industrial and artisanal bakers worldwide.
-
B.
Murray & Roberts
Murray & Roberts is a major South African engineering and construction group known for delivering large, complex infrastructure and building projects worldwide.
-
C.
Morar Group
The Morar Group is a sequence of metamorphic rock formations in the Scottish Highlands that forms part of the ancient Moine geology.
-
D.
Kvaerner
Kvaerner is a Norwegian engineering and construction company historically prominent in the shipbuilding and offshore oil and gas industries.
-
E.
Tractebel
Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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. |
Created at: April 17, 2026, 4:06 p.m.