Triple
T26575614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ADX Florence |
E666939
|
entity |
| Predicate | mealPolicy |
P73753
|
FINISHED |
| Object | meals served in cells |
—
|
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: meals served in cells | Statement: [ADX Florence, mealPolicy, meals served in cells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mealPolicy Context triple: [ADX Florence, mealPolicy, meals served in cells]
-
A.
hasDiningPolicy
chosen
Indicates that an entity enforces or follows a specific set of rules or guidelines related to dining or meal-related activities.
-
B.
eatingPermitted
Indicates that an entity is allowed or authorized to eat in a given context or situation.
-
C.
hasBeveragePolicy
Indicates that an entity has an established rule or set of guidelines governing the provision, consumption, or management of beverages.
-
D.
venuePolicy
Indicates the rules or guidelines that govern how activities or events may be conducted at a particular venue.
-
E.
bookingPolicy
Indicates the rules or conditions that govern how bookings or reservations can be made, modified, or canceled between parties.
- 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_69ee9cfa21c081909e4e36e087debfc6 |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f614dd573c8190b5b26c7a41b737ec |
completed | May 2, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 2 a.m.