Triple
T23103164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Mia |
E576088
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Amelia |
—
|
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: Amelia | Statement: [Princess Mia, givenName, Amelia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amelia Context triple: [Princess Mia, givenName, Amelia]
-
A.
Amelia
chosen
Amelia was a British princess of the early 18th century, the daughter of King George II and Queen Caroline of Ansbach.
-
B.
Amelia
"Amelia" is a track featured on the album *Travelogue*, likely contributing a reflective or journey-themed element to the record’s overall narrative.
-
C.
Amelia
Amelia is a feminine given name of Latin and Germanic origin, commonly used in many countries and often associated with figures such as aviation pioneer Amelia Earhart.
-
D.
Amelia
Amelia is the terror-stricken protagonist of the famous “Zuni doll” segment in the 1975 horror anthology film Trilogy of Terror.
-
E.
Amelia
Amelia is a supporting character in the graphic novel "American Born Chinese," contributing to its exploration of identity, culture, and adolescence.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18deaacbc8190a97e64e1cf39cdd6 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.