Triple
T15958017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moonlight in Vermont |
E386984
|
entity |
| Predicate | subject |
P450
|
FINISHED |
| Object |
moonlight
Moonlight is the gentle, reflected light from the Moon that softly illuminates the night sky.
|
E1185963
|
NE FINISHED |
How this triple was built (4 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: moonlight | Statement: [Moonlight in Vermont, subject, moonlight]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: moonlight Context triple: [Moonlight in Vermont, subject, moonlight]
-
A.
In the Moonlight
"In the Moonlight" is a jazz vocal album by Russian-Canadian singer Sophie Milman, showcasing her smooth interpretations of standards and contemporary songs.
-
B.
Moony
Moony is the nickname of Remus Lupin, the kind and bookish werewolf who taught Defence Against the Dark Arts at Hogwarts in the Harry Potter series.
-
C.
Mr. Moonlight
"Mr. Moonlight" is a cover of a bluesy rock and roll song recorded by the Beatles and included on their 1964 album Beatles for Sale.
-
D.
Mr. Moonlight
Mr. Moonlight is a studio album by the British-American rock band Foreigner, known for its melodic rock sound and marking a later phase in the band’s discography.
-
E.
Void Moon
Void Moon is a crime novel by Michael Connelly that follows a female ex-con drawn back into a high-stakes Las Vegas heist.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: moonlight Triple: [Moonlight in Vermont, subject, moonlight]
Generated description
Moonlight is the gentle, reflected light from the Moon that softly illuminates the night sky.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: moonlight Target entity description: Moonlight is the gentle, reflected light from the Moon that softly illuminates the night sky.
-
A.
In the Moonlight
"In the Moonlight" is a jazz vocal album by Russian-Canadian singer Sophie Milman, showcasing her smooth interpretations of standards and contemporary songs.
-
B.
Moony
Moony is the nickname of Remus Lupin, the kind and bookish werewolf who taught Defence Against the Dark Arts at Hogwarts in the Harry Potter series.
-
C.
Mr. Moonlight
"Mr. Moonlight" is a cover of a bluesy rock and roll song recorded by the Beatles and included on their 1964 album Beatles for Sale.
-
D.
Mr. Moonlight
Mr. Moonlight is a studio album by the British-American rock band Foreigner, known for its melodic rock sound and marking a later phase in the band’s discography.
-
E.
Void Moon
Void Moon is a crime novel by Michael Connelly that follows a female ex-con drawn back into a high-stakes Las Vegas heist.
- F. None of above. chosen
Provenance (5 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156fd7ce08190b5db4b486ccb6e40 |
completed | April 16, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe7e76d481909e6f1d1ea33edd60 |
completed | May 9, 2026, 11:08 p.m. |
| NEDg | Description generation | batch_69ffbf3e80b08190899262a9d03c0e93 |
completed | May 9, 2026, 11:11 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffbfc0d1548190b7d2e9e10e837f0b |
completed | May 9, 2026, 11:14 p.m. |
Created at: April 10, 2026, 4:53 a.m.