Triple
T27878448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stillwater |
E705016
|
entity |
| Predicate | inUniverseSongTitle |
P166197
|
FINISHED |
| Object |
Fever Dog
"Fever Dog" is a fictional 1970s-style rock song performed by the band Stillwater in the film *Almost Famous*, embodying the era’s classic rock sound.
|
E1793008
|
NE FINISHED |
How this triple was built (3 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: Fever Dog | Statement: [Stillwater, inUniverseSongTitle, Fever Dog]
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: Fever Dog Triple: [Stillwater, inUniverseSongTitle, Fever Dog]
Generated description
"Fever Dog" is a fictional 1970s-style rock song performed by the band Stillwater in the film *Almost Famous*, embodying the era’s classic rock sound.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseSongTitle Context triple: [Stillwater, inUniverseSongTitle, Fever Dog]
-
A.
isSongIn
Indicates that a particular song is contained within or belongs to a specified collection, such as an album, playlist, or soundtrack.
-
B.
isTitleCharacterOfSong
Indicates that a character is mentioned in or constitutes the title of a specific song.
-
C.
hasSongTitle
Indicates that an entity (such as a song or musical work) bears or is associated with a specific song title.
-
D.
sangSongsIn
Indicates that one entity performed or vocalized songs in the context, location, or event associated with another entity.
-
E.
clubSongTitle
Indicates that a song serves as the official or associated song of a particular club, identified by its title.
- F. None of above. chosen
Provenance (7 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_69ef84111bb4819084298f994b31c62f |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f66003a3f48190a2ba6da5aafbb5cb |
completed | May 2, 2026, 8:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a130352ca808190a21fd9edc81cda04 |
completed | May 24, 2026, 1:55 p.m. |
| NEDg | Description generation | batch_6a1303cdd46c8190a45f59338fc449f8 |
completed | May 24, 2026, 1:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a13045f3af48190898773ba0e82ba71 |
completed | May 24, 2026, 1:59 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
| PDg | Predicate description generation | batch_69f65f75ac608190a62cd6afce14f68e |
completed | May 2, 2026, 8:32 p.m. |
Created at: April 27, 2026, 6:28 p.m.