Triple
T18645757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pearl |
E455800
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Half Moon |
—
|
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: Half Moon | Statement: [Pearl, hasPart, Half Moon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Half Moon Context triple: [Pearl, hasPart, Half Moon]
-
A.
Half Moon
chosen
Half Moon is the English name of the Dutch ship Halve Maen, famed for Henry Hudson’s 1609 voyage that led to the exploration of present-day New York.
-
B.
Halfmoon
Halfmoon is a suburban town in eastern New York State known for its residential communities and proximity to the Capital District.
-
C.
Orange Moon
"Orange Moon" is a soulful, jazz-inflected neo-soul song by Erykah Badu from her acclaimed 2000 album *Mama’s Gun*.
-
D.
Favorites of the Moon
Favorites of the Moon is a 1984 French-Georgian satirical film by director Otar Iosseliani, known for its ensemble storytelling, minimal dialogue, and whimsical critique of bourgeois society.
-
E.
South Moon Under
South Moon Under is a 1933 novel by Marjorie Kinnan Rawlings that portrays the harsh, rustic life of Florida backwoods settlers and helped establish her reputation in American literature.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5500d69648190800da65de0c191b8 |
completed | April 19, 2026, 9:58 p.m. |
Created at: April 10, 2026, 11:47 a.m.