Triple
T36351518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freddie Thorne |
E895216
|
entity |
| Predicate | formerComradeInArms |
P66534
|
FINISHED |
| Object | Thomas Shelby |
—
|
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: Thomas Shelby | Statement: [Freddie Thorne, formerComradeInArms, Thomas Shelby]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerComradeInArms Context triple: [Freddie Thorne, formerComradeInArms, Thomas Shelby]
-
A.
unitComrades
Indicates that two or more entities serve or operate together as comrades within the same unit or group.
-
B.
formerAllyOf
chosen
Indicates that an entity was once an ally of another entity but that alliance has since ended.
-
C.
formerEnemyOf
Indicates that one entity was previously an enemy of another entity, but that adversarial relationship no longer holds.
-
D.
brotherOrAlly
Indicates a relationship where one entity is either a brother of, or an allied supporter/partner to, another entity.
-
E.
formerFriend
Indicates that two entities were once friends but are no longer in a friendship relationship.
- 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a009a0e1fa481909ed881012009b268 |
completed | May 10, 2026, 2:45 p.m. |
| PD | Predicate disambiguation | batch_6a0092e9fcb08190a966d720684f25ec |
completed | May 10, 2026, 2:15 p.m. |
Created at: May 3, 2026, 4:09 p.m.