Triple
T34338905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Run Like Hell |
E881228
|
entity |
| Predicate | hasNotableMusicVideo |
P63183
|
FINISHED |
| Object | The Wall film sequence |
E1429441
|
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 Wall film sequence | Statement: [Run Like Hell, hasNotableMusicVideo, The Wall film sequence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableMusicVideo Context triple: [Run Like Hell, hasNotableMusicVideo, The Wall film sequence]
-
A.
hasMusicVideo
Indicates that a piece of media (typically a song) is associated with or accompanied by a music video.
-
B.
hasMusicVideoCharacteristic
Indicates that a music video possesses a specific attribute, feature, or quality.
-
C.
hasFictionalMusicVideo
Indicates that a subject has an associated music video that exists only within a fictional or narrative context, rather than as a real-world production.
-
D.
musicVideoNotableFor
chosen
Indicates that a music video is especially recognized or noteworthy for a particular feature, element, or aspect.
-
E.
hasViralMusicVideo
Indicates that an entity possesses or is associated with a music video that has achieved viral popularity or widespread online circulation.
- F. None of above.
Provenance (4 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_69f349bc55e881908c8e338ef76b0043 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0317eaf4e88190a6f6419cb4ef7547 |
completed | May 12, 2026, 12:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36f9df678481909cd150924dddfeb3 |
completed | June 20, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_6a03179da394819095e3d346c3785d74 |
completed | May 12, 2026, 12:05 p.m. |
Created at: May 1, 2026, 1:58 a.m.