Triple
T22244605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IMG |
E549809
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object | IMG Media |
—
|
NE NERFINISHED |
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: IMG Media | Statement: [IMG, hasDivision, IMG Media]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IMG Media Context triple: [IMG, hasDivision, IMG Media]
-
A.
IMG
chosen
IMG is a global sports, events, and talent management company known for representing athletes and models and producing major sporting and fashion events.
-
B.
Images
Images is a set of impressionistic piano pieces by Claude Debussy that evoke vivid, atmospheric soundscapes through innovative harmony and tone color.
-
C.
Images
Images is a 1972 psychological horror film directed by Robert Altman, known for its surreal, fragmented portrayal of a woman’s mental breakdown.
-
D.
MPIMG
MPIMG is a leading research institute of the Max Planck Society focused on advancing molecular genetics and genomics.
-
E.
Media Res
Media Res is a television and film production company best known for producing high-profile, prestige series for major streaming platforms.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f132170e5081909b9dbb204abf2a45 |
completed | April 28, 2026, 10:17 p.m. |
Created at: April 16, 2026, 8:38 p.m.