Triple
T20012547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gratiano |
E494623
|
entity |
| Predicate | speaksTo |
P40250
|
FINISHED |
| Object | Portia |
—
|
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: Portia | Statement: [Gratiano, speaksTo, Portia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Portia Context triple: [Gratiano, speaksTo, Portia]
-
A.
Portia
Portia is an inner moon of Uranus that helps gravitationally shape and maintain parts of the planet’s ring system.
-
B.
Portia
chosen
Portia is a wealthy, intelligent, and quick-witted heiress in Shakespeare’s play "The Merchant of Venice," renowned for her resourcefulness and famous courtroom disguise as a male lawyer.
-
C.
Portia Doubleday
Portia Doubleday is an American actress best known for her role as Angela Moss in the television series "Mr. Robot."
-
D.
Portia Sperr
Portia Sperr is an American museum professional best known for founding Philadelphia’s Please Touch Museum, one of the first museums in the United States designed specifically for children’s hands-on learning.
-
E.
Portia Davenport
Portia Davenport is a wealthy, naive, and eccentric young woman who serves as one of the core comedic characters in the dark comedy TV series "Search Party."
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66238f434819083b11458179bb601 |
completed | April 20, 2026, 5:28 p.m. |
Created at: April 11, 2026, 3:34 p.m.