Triple
T35224645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernest-Jean Sarrasine |
E1017056
|
entity |
| Predicate | romanticInterestType |
P122344
|
FINISHED |
| Object | castrato singer |
—
|
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: castrato singer | Statement: [Ernest-Jean Sarrasine, romanticInterestType, castrato singer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanticInterestType Context triple: [Ernest-Jean Sarrasine, romanticInterestType, castrato singer]
-
A.
formerRomanticInterest
Indicates that one entity previously had a romantic relationship or attraction toward another entity, but that romantic connection has since ended.
-
B.
loveInterestType
chosen
Indicates the specific kind or category of romantic or affectionate relationship that exists between the related entities.
-
C.
loveInterestPortrayedBy
Indicates that a character’s romantic interest is depicted or played by a particular actor or performer.
-
D.
romanticOrSexualPartners
Indicates that the entities have been, are, or are intended to be involved as romantic and/or sexual partners with each other.
-
E.
romanceType
Indicates the specific kind or category of romantic relationship that exists between the related 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_69f76de072908190ab65038a8a7b6a79 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:02 p.m.