Triple
T33871424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Janet Hodgson |
E868216
|
entity |
| Predicate | hasMediaAppearanceAsSelf |
P69406
|
FINISHED |
| Object | interviews about the Enfield poltergeist |
—
|
LITERAL 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: interviews about the Enfield poltergeist | Statement: [Janet Hodgson, hasMediaAppearanceAsSelf, interviews about the Enfield poltergeist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMediaAppearanceAsSelf Context triple: [Janet Hodgson, hasMediaAppearanceAsSelf, interviews about the Enfield poltergeist]
-
A.
hasMediaAppearanceIn
Indicates that an entity appears or is featured as media content within a specified media work, program, or publication.
-
B.
mediaAppearanceWith
Indicates that two or more entities appeared together in the same media context, such as a show, interview, article, or broadcast.
-
C.
mediaAppearanceType
chosen
Indicates the specific kind or category of media appearance associated with an entity (e.g., interview, feature, cameo, or performance).
-
D.
hasMediaAspect
Indicates that something possesses a particular media-related characteristic, format, or attribute.
-
E.
hasMediaStereotype
Indicates that an entity is associated with a commonly held, simplified, and often biased portrayal in media.
- F. None of above.
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_69f34995029081909ede0f7df73d1a5e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fefa064ab48190925759950d0d94d9 |
completed | May 9, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69fef96ae5d08190b027435753c44821 |
completed | May 9, 2026, 9:07 a.m. |
Created at: May 1, 2026, 1:47 a.m.