Triple
T969641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flag of the Isle of Man |
E20916
|
entity |
| Predicate | symbolOrigin |
P3654
|
FINISHED |
| Object | medieval heraldry |
—
|
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: medieval heraldry | Statement: [Flag of the Isle of Man, symbolOrigin, medieval heraldry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: symbolOrigin Context triple: [Flag of the Isle of Man, symbolOrigin, medieval heraldry]
-
A.
symbolType
Indicates the classification or category of a symbol based on its role, form, or function within a given system.
-
B.
symbolDescription
Indicates that a symbol is associated with or defined by a particular descriptive explanation or meaning.
-
C.
hasNameOrigin
Indicates that the origin or source of an entity’s name is specified by the related entity.
-
D.
hasOriginIn
chosen
Indicates that something begins, arises, or is derived from a specified source, place, or cause.
-
E.
hasAcronymOrigin
Indicates that an acronym is derived from or originates from a specific longer expression or name.
- 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_69a493b33d2c81909c52c369d3ca8436 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b4497d688190b59c3a195e377080 |
completed | March 1, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a579888190afb489ac9fe8391c |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.