Triple
T6416760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh Martin |
E127847
|
entity |
| Predicate | wroteSong |
P2831
|
FINISHED |
| Object | The Boy Next Door |
E121655
|
NE FINISHED |
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: The Boy Next Door | Statement: [Hugh Martin, wroteSong, The Boy Next Door]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Boy Next Door Context triple: [Hugh Martin, wroteSong, The Boy Next Door]
-
A.
The Boy Next Door
chosen
"The Boy Next Door" is a romantic ballad from the 1944 MGM musical film *Meet Me in St. Louis*, famously performed by Judy Garland.
-
B.
The Girl Next Door
The Girl Next Door is a 2004 romantic comedy film about a high school senior who falls for his new neighbor, only to discover she is a former porn star, starring Emile Hirsch and Elisha Cuthbert.
-
C.
Girl Next Door
"Girl Next Door" is a track featured on the hip-hop album "King of Stage" by rapper and producer Dana Dane.
-
D.
Dear Boy
"Dear Boy" is a song by the Indian musician Ram.
-
E.
Oh Boy
"Oh Boy" is a 2002 hit hip-hop single by Cam'ron featuring Juelz Santana, known for its catchy pitched-up soul sample and major impact on early-2000s rap.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c0083815208190a9b299b8e0640218 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c068ea06b08190901e0c0a18fd5170 |
completed | March 22, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c64bb79f74819088a6e30a9deb8616 |
completed | March 27, 2026, 9:19 a.m. |
Created at: March 22, 2026, 4:42 p.m.