Triple
T36864491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Singh |
E911032
|
entity |
| Predicate | hasLoveLetterExchangeWith |
P73290
|
FINISHED |
| Object | Susie Salmon |
—
|
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: Susie Salmon | Statement: [Ray Singh, hasLoveLetterExchangeWith, Susie Salmon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLoveLetterExchangeWith Context triple: [Ray Singh, hasLoveLetterExchangeWith, Susie Salmon]
-
A.
lettersWrittenBetween
chosen
Indicates that letters have been written and exchanged between the two entities, reflecting a mutual correspondence.
-
B.
correspondedWith
Indicates that two entities engaged in mutual communication, typically by exchanging messages or letters over a period of time.
-
C.
hasLetterBy
Indicates that an entity possesses or is associated with a letter authored or sent by another entity.
-
D.
hasFanMail
Indicates that one entity has received or possesses fan mail from another entity.
-
E.
hasFriendship
Indicates a mutual, positive social relationship of friendship existing between two 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_69f76e80f6f0819091cba8e19b269615 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff70ecc1a481909571b18d56d982b8 |
completed | May 9, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69ff70322a3c8190837840ea42cd3093 |
completed | May 9, 2026, 5:34 p.m. |
Created at: May 3, 2026, 4:13 p.m.