Triple
T35365460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eli Roth's History of Horror |
E1021615
|
entity |
| Predicate | hasCompanionPodcast |
P122192
|
FINISHED |
| Object | Eli Roth's History of Horror: Uncut |
E1021615
|
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: Eli Roth's History of Horror: Uncut | Statement: [Eli Roth's History of Horror, hasCompanionPodcast, Eli Roth's History of Horror: Uncut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompanionPodcast Context triple: [Eli Roth's History of Horror, hasCompanionPodcast, Eli Roth's History of Horror: Uncut]
-
A.
hasPodcast
Indicates that an entity produces, owns, or is associated with a podcast.
-
B.
hasCompanionContent
chosen
Indicates that one piece of content is accompanied by related or supplementary content intended to be used or consumed together.
-
C.
appearsInPodcast
Indicates that an entity is featured or participates as content in a particular podcast episode or series.
-
D.
hasCompanionPillar
Indicates that an entity is associated with or supported by a corresponding companion pillar.
-
E.
hasEpisodeAbout
Indicates that a particular episode (such as of a show, podcast, or series) focuses on, discusses, or is centered around a specified subject or topic.
- 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_69f76df000488190ab7c97f565677055 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3836a569d881908b37895c98357429 |
completed | June 21, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_6a037a0324d08190ac5b610cc0f6a38c |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:03 p.m.