Triple
T16215600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilly Holbrook |
E393584
|
entity |
| Predicate | relationshipTypeWithSkeeterPhelan |
P115552
|
FINISHED |
| Object | former friend turned adversary |
—
|
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: former friend turned adversary | Statement: [Hilly Holbrook, relationshipTypeWithSkeeterPhelan, former friend turned adversary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithSkeeterPhelan Context triple: [Hilly Holbrook, relationshipTypeWithSkeeterPhelan, former friend turned adversary]
-
A.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
B.
opusRelationship
Indicates a relationship between creative works (opuses), such as versions, adaptations, or parts within a larger compositional whole.
-
C.
relationshipTypeWithGoosefatBill
chosen
Indicates the specific nature or category of relationship that an entity has with GoosefatBill.
-
D.
termRelationTo
Indicates a general relational association between one term and another, without specifying the exact nature of that relationship.
-
E.
relationshipPlannedWith
Indicates that a relationship between two entities has been intentionally arranged or scheduled to occur in the future.
- 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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e227f4685c8190aa1e9304e4a62d13 |
completed | April 17, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69e219e94a448190b73a4e6aa374eb4a |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:03 a.m.