Triple
T38170067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kestra Troi |
E1000045
|
entity |
| Predicate | memorySuppressedBy |
P91075
|
FINISHED |
| Object | Lwaxana Troi |
—
|
NE NERFINISHED |
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: Lwaxana Troi | Statement: [Kestra Troi, memorySuppressedBy, Lwaxana Troi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorySuppressedBy Context triple: [Kestra Troi, memorySuppressedBy, Lwaxana Troi]
-
A.
suppressedIn
chosen
Indicates that one entity’s presence, activity, or expression is reduced, inhibited, or prevented by another entity or condition.
-
B.
suppressedDuring
Indicates that one event, action, or state is actively prevented, inhibited, or held back while another specified event, condition, or time period is occurring.
-
C.
suppressedOn
Indicates that one entity is intentionally prevented, hidden, or blocked from being shown, executed, or taking effect in the context of another entity.
-
D.
memoryPreservedBy
Indicates that a memory or information is maintained, retained, or kept intact through the action, mechanism, or influence of the associated entity.
-
E.
memoryState
Indicates the condition or configuration of an entity’s stored information at a particular point in time.
- 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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:29 p.m.