Triple
T22234377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iphemache |
E549550
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | Leda |
—
|
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: Leda | Statement: [Iphemache, siblingOf, Leda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leda Context triple: [Iphemache, siblingOf, Leda]
-
A.
Leda
chosen
Leda is a figure in Greek mythology, a Spartan queen best known as the mother of Helen of Troy and the Dioscuri after being seduced by Zeus.
-
B.
Leda
Leda is a river in northwestern Germany that serves as a significant tributary of the Ems.
-
C.
Leda
Leda is a small, irregular outer moon of Jupiter belonging to the planet’s distant, retrograde satellite group.
-
D.
Leda (young)
Leda (young) is the younger version of the protagonist in Elena Ferrante’s novel and its film adaptation "The Lost Daughter," depicted during her tumultuous years as a young mother and academic.
-
E.
Persiles
Persiles is the adventurous noble protagonist of Miguel de Cervantes’ late romance novel "Los trabajos de Persiles y Sigismunda," known for his perilous travels and disguised identity.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf61504819093e70bee4c575d1c |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:38 p.m.