Triple
T10642744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Of Friendship |
E250762
|
entity |
| Predicate | hasCharacterizationOfFriendship |
P89493
|
FINISHED |
| Object | union of souls |
—
|
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: union of souls | Statement: [Of Friendship, hasCharacterizationOfFriendship, union of souls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCharacterizationOfFriendship Context triple: [Of Friendship, hasCharacterizationOfFriendship, union of souls]
-
A.
hasFriendship
Indicates a mutual, positive social relationship of friendship existing between two entities.
-
B.
relationshipCharacterizedAs
chosen
Indicates that one relationship is described, defined, or typified in terms of another specified characteristic or relational type.
-
C.
isFriendOfProtagonist
Indicates that one entity is a friend or close ally of the story’s main character.
-
D.
basedOnCharactersRelationship
Indicates that something is determined or derived from the relationship between the characters involved.
-
E.
companionshipStatus
Indicates the current state or condition of a relationship of companionship 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfce1ddc8190893fe6f7b047b56b |
completed | April 8, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69d6dd83b114819098e84dc658e82d7e |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:05 p.m.