Triple
T3097288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Carmichael |
E64627
|
entity |
| Predicate | relationshipArc |
P39999
|
FINISHED |
| Object | reunites with Donna Sheridan |
—
|
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: reunites with Donna Sheridan | Statement: [Sam Carmichael, relationshipArc, reunites with Donna Sheridan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipArc Context triple: [Sam Carmichael, relationshipArc, reunites with Donna Sheridan]
-
A.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
B.
termRelationTo
Indicates a general relational association between one term and another, without specifying the exact nature of that relationship.
-
C.
relationshipPlannedWith
Indicates that a relationship between two entities has been intentionally arranged or scheduled to occur in the future.
-
D.
semanticRelation
Indicates a general meaning-based connection between two entities, such as similarity, implication, or conceptual association.
-
E.
relationshipDynamic
chosen
Indicates a changing or evolving pattern of interaction between entities, such as shifts in their roles, closeness, or influence over 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_69ad857dc98481909e585dc3372e3ed5 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada23cbe3c8190b7ec5cfd464a1ca8 |
completed | March 8, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69ad9df06ed88190809f0683122caa5a |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:03 p.m.