Triple
T16729029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broken Road |
E406535
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | Broken Road |
E406535
|
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: Broken Road | Statement: [Broken Road, hasTitle, Broken Road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Broken Road Context triple: [Broken Road, hasTitle, Broken Road]
-
A.
Broken Road
chosen
"Broken Road" is a track by Kanye West from his unfinished and Stem Player–exclusive album "Donda 2."
-
B.
Long Road
"Long Road" is a reggae song by Jamaican singer Junior Reid, known for its socially conscious lyrics and distinctive vocal style.
-
C.
Long Road
Long Road is a notable street in Cambridge, England, known for its educational institutions and as a key route in the city's southern area.
-
D.
Beautiful Road
"Beautiful Road" is an album by American singer-songwriter Kate Taylor that showcases her blend of folk, rock, and roots music.
-
E.
Anywhere on This Road
"Anywhere on This Road" is a haunting, world-music-infused song by singer-songwriter Lhasa de Sela, known for its melancholic atmosphere and poetic lyrics.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3874ad5b481908199e4d99ac4225e |
completed | April 18, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a519a89081909456bb6fc25d9234 |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:20 a.m.