Triple
T22957629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The City in the Middle of the Night |
E570803
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Alyssa |
—
|
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: Alyssa | Statement: [The City in the Middle of the Night, mainCharacter, Alyssa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alyssa Context triple: [The City in the Middle of the Night, mainCharacter, Alyssa]
-
A.
Alyssa
chosen
Alyssa is a feminine given name that gained widespread popularity in the late 20th century, partly due to its use by American actress Alyssa Milano.
-
B.
Allison
Allison is a common English-language surname of Scottish and Irish origin, often derived from "son of Alice" or "son of Alan."
-
C.
Allison
Allison is a key character in the film "Hocus Pocus," known as Max Dennison’s love interest and ally in battling the Sanderson sisters.
-
D.
Allison
Allison is a free-spirited, eccentric love interest played by Zooey Deschanel in the comedy film "Yes Man."
-
E.
Allison
Allison is the given first name of the fictional character Sonny Munroe from the Disney Channel series "Sonny with a Chance."
- 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f21e588190a5a88a15c1b55dea |
completed | April 29, 2026, 3:58 a.m. |
Created at: April 17, 2026, 3:47 p.m.