Triple
T15240349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edmund Tyrone |
E364237
|
entity |
| Predicate | relationshipToAlcohol |
P55898
|
FINISHED |
| Object | heavy drinker |
—
|
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: heavy drinker | Statement: [Edmund Tyrone, relationshipToAlcohol, heavy drinker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToAlcohol Context triple: [Edmund Tyrone, relationshipToAlcohol, heavy drinker]
-
A.
associatedWithSubstance
Indicates that one entity has a relevant connection or involvement with a particular substance, such as use, presence, exposure, or composition.
-
B.
drinkingHabit
Indicates an entity’s typical pattern or frequency of consuming alcoholic or other beverages.
-
C.
hasAddictionOrIssue
Indicates that an entity experiences a dependency, compulsion, or problematic issue related to a substance, behavior, or condition.
-
D.
drinksAlcohol
chosen
Indicates that an entity consumes alcoholic beverages.
-
E.
alcoholRange
Indicates the range or interval of alcohol content associated with an entity (e.g., minimum and maximum alcohol level).
- 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_69d85a0dde7481908fc64d1e82d5d20d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007db9a148190aadea8d5f8b6b261 |
completed | April 15, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69deca899d5c8190be4a7c71e1683c69 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:13 a.m.