Triple
T10880926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De Beers |
E256914
|
entity |
| Predicate | focusShift |
P96211
|
FINISHED |
| Object | from supply control to branding |
—
|
LITERAL 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: from supply control to branding | Statement: [De Beers, focusShift, from supply control to branding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusShift Context triple: [De Beers, focusShift, from supply control to branding]
-
A.
focusType
Indicates the specific kind or category of focus or attention that is being applied to or associated with an entity or interaction.
-
B.
focusOf
Indicates that one entity is the primary subject, target, or center of attention, activity, or interest for another entity.
-
C.
focusFeature
Indicates that one entity is the primary or emphasized feature, aspect, or attribute being highlighted or concentrated on in relation to another.
-
D.
focusPosition
Indicates the spatial or logical position at which attention, concentration, or processing is currently directed within a given context.
-
E.
focusModel
Indicates that one entity serves as the primary or central model that another entity is directed toward, based on, or concentrated on.
- F. None of above. chosen
Provenance (4 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751b031a88190b1182dfc1f520264 |
completed | April 9, 2026, 7:13 a.m. |
| PD | Predicate disambiguation | batch_69d70d360c388190a3d829fe8862434f |
completed | April 9, 2026, 2:21 a.m. |
| PDg | Predicate description generation | batch_69d7101de31c819090707635f6790559 |
completed | April 9, 2026, 2:34 a.m. |
Created at: April 8, 2026, 9:21 p.m.