Triple
T27782542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hill Valley Clock Tower |
E699370
|
entity |
| Predicate | realWorldStudio |
P163564
|
FINISHED |
| Object | Universal Pictures |
—
|
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: Universal Pictures | Statement: [Hill Valley Clock Tower, realWorldStudio, Universal Pictures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: realWorldStudio Context triple: [Hill Valley Clock Tower, realWorldStudio, Universal Pictures]
-
A.
realWorldParallel
Indicates that one entity has a counterpart, analogy, or directly corresponding situation in the real world relative to another entity.
-
B.
realWorldInstanceOf
Indicates that an entity is a concrete, real-world example or occurrence of a more abstract type, concept, or class.
-
C.
sisterStudio
Indicates that two studios are related as sister studios, typically sharing common ownership, affiliation, or close partnership within the same corporate or organizational structure.
-
D.
setDesignerInReality
Indicates that a particular person serves as the set designer within the context of a specific reality-based production or show.
-
E.
liveOrStudio
Indicates whether something (typically a performance or recording) was done live or in a studio setting.
- F. None of above. chosen
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_69ef6a4b5a9081909c9111396c2be3d2 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f6397b64f881909d811225e57aac5e |
completed | May 2, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 5:11 p.m.