Triple
T11512992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milan public prosecutor's office |
E272959
|
entity |
| Predicate | focusDuringManiPulite |
P31
|
FINISHED |
| Object | bribery in public contracts |
—
|
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: bribery in public contracts | Statement: [Milan public prosecutor's office, focusDuringManiPulite, bribery in public contracts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusDuringManiPulite Context triple: [Milan public prosecutor's office, focusDuringManiPulite, bribery in public contracts]
-
A.
focusShift
Indicates a change in attention or emphasis from one entity or topic to another.
-
B.
focusType
Indicates the specific kind or category of focus or attention that is being applied to or associated with an entity or interaction.
-
C.
focusMechanism
Indicates the method or process by which attention or emphasis is directed toward a particular entity or aspect within a context.
-
D.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
E.
focusFeature
Indicates that one entity is the primary or emphasized feature, aspect, or attribute being highlighted or concentrated on in relation to another.
- F. None of above.
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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d86db7af688190b68668eb39d382a8 |
completed | April 10, 2026, 3:25 a.m. |
| PD | Predicate disambiguation | batch_69d80876e5f0819088cff2e72f773cf6 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:36 p.m.