Triple
T34588689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sparks (mad scientists) |
E888116
|
entity |
| Predicate | hasInUniverseTerm |
P2920
|
FINISHED |
| Object | Spark |
—
|
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: Spark | Statement: [Sparks (mad scientists), hasInUniverseTerm, Spark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInUniverseTerm Context triple: [Sparks (mad scientists), hasInUniverseTerm, Spark]
-
A.
hasNameInUniverse
Indicates that an entity is known by a particular name within a specific fictional or defined universe.
-
B.
hasTerm
chosen
Indicates that an entity includes, is associated with, or is defined by a specific term or condition.
-
C.
hasInUniverseLocationRelation
Indicates a relationship where an entity is associated with, or situated at, a specific location within a fictional or defined universe or setting.
-
D.
inUniverseType
Indicates that one entity exists within, or is categorized as belonging to, a particular fictional or conceptual universe type defined by the other entity.
-
E.
hasLanguageInUniverse
Indicates that a particular language exists or is used within a specified fictional or conceptual universe.
- 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_69f349d3bfcc81909874c99e646fb3ea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00372ff0e48190b3ed91f9bae9da6c |
completed | May 10, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_6a00359c1b8481909c1e43df9f5a789a |
completed | May 10, 2026, 7:37 a.m. |
Created at: May 1, 2026, 2:03 a.m.