Triple
T11996933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | spinning top totem |
E285554
|
entity |
| Predicate | ambiguitySource |
P71448
|
FINISHED |
| Object | cut to black before top falls or stays spinning |
—
|
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: cut to black before top falls or stays spinning | Statement: [spinning top totem, ambiguitySource, cut to black before top falls or stays spinning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ambiguitySource Context triple: [spinning top totem, ambiguitySource, cut to black before top falls or stays spinning]
-
A.
languageAmbiguity
Indicates that the meaning, interpretation, or reference of a linguistic expression is unclear or can be understood in multiple ways.
-
B.
supportsDisambiguationOf
Indicates that one entity helps clarify or distinguish the correct meaning or identity of another entity among multiple possible interpretations.
-
C.
narrativeAmbiguity
chosen
Indicates that a narrative contains unclear, open-ended, or multiple possible interpretations of events, motivations, or outcomes.
-
D.
viewOnAmbiguity
Indicates an entity’s stance or attitude toward ambiguity, such as how much uncertainty or vagueness it accepts or prefers.
-
E.
hasDisambiguationNote
Indicates that there is an explanatory note used to distinguish this entity or term from other entities or terms with similar or identical names.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c172788190b92042e9d10a48bf |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902b245cc8190af96a9c2bd9c6250 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:46 p.m.