Triple
T33753463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Knightley |
E864907
|
entity |
| Predicate | hasCurrentHabit |
P41014
|
FINISHED |
| Object | abstaining from alcohol |
—
|
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: abstaining from alcohol | Statement: [Andy Knightley, hasCurrentHabit, abstaining from alcohol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCurrentHabit Context triple: [Andy Knightley, hasCurrentHabit, abstaining from alcohol]
-
A.
hasHabit
chosen
Indicates that an entity regularly performs, practices, or exhibits a particular behavior or routine.
-
B.
hasTypeOfHabit
Indicates that an entity exhibits or follows a particular kind or category of habit.
-
C.
hasCurrent
Indicates that an entity presently possesses, exhibits, or is associated with a particular state, attribute, or resource at the current time.
-
D.
hasActivityIn
Indicates that an entity engages in or performs a particular activity within a specified context, location, or domain.
-
E.
hasOngoing
Indicates that one entity is currently engaged in, experiencing, or maintaining an activity, state, or process that has not yet concluded.
- 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_69f3498c35f881909df279ae4270f831 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd8e5f7c4c8190ab8e2f2a7bb1bd79 |
completed | May 8, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fd8d8a16f08190b9e880901bfa44fe |
completed | May 8, 2026, 7:15 a.m. |
Created at: May 1, 2026, 1:45 a.m.