Triple
T22080762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anne Shirley forms a close friendship with Diana Barry |
E545641
|
entity |
| Predicate | relationshipQuality |
P137672
|
FINISHED |
| Object | loyal |
—
|
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: loyal | Statement: [Anne Shirley forms a close friendship with Diana Barry, relationshipQuality, loyal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipQuality Context triple: [Anne Shirley forms a close friendship with Diana Barry, relationshipQuality, loyal]
-
A.
relationshipDynamic
Indicates a changing or evolving pattern of interaction between entities, such as shifts in their roles, closeness, or influence over time.
-
B.
relationshipDurationWith
Indicates the length of time that a specified relationship between two entities has existed or is expected to last.
-
C.
relationshipImpact
Indicates how one entity’s relationship with another affects or changes those entities or their interaction.
-
D.
stateOfRelations
chosen
Indicates the current nature or condition of the relationship between two or more entities, such as whether it is friendly, hostile, neutral, or otherwise characterized.
-
E.
relationshipOutcome
Indicates the result or consequence that arises from a particular relationship between two or more entities.
- 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128b6338481908e6bb0187cdd42af |
completed | April 28, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69e71b20ec50819096ac196c798f8e3c |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:28 p.m.