Triple
T31267216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erin (female figure) holding a harp |
E797285
|
entity |
| Predicate | country personification of |
P81304
|
FINISHED |
| Object | Ireland |
—
|
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: Ireland | Statement: [Erin (female figure) holding a harp, country personification of, Ireland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: country personification of Context triple: [Erin (female figure) holding a harp, country personification of, Ireland]
-
A.
isPersonificationOf
chosen
Indicates that one entity represents or embodies an abstract concept, quality, or non-human thing in human form.
-
B.
genderPersonification
Indicates that a non-human entity is represented or treated as having a specific gender.
-
C.
countrySubject
Indicates that the subject entity is a country that is the main actor, topic, or focus in the described relation or statement.
-
D.
isFoodPersonification
Indicates that a food item is depicted or treated as if it were a person, with human-like traits, roles, or behaviors.
-
E.
countryTheme
Indicates that something is associated with or represents a thematic focus on a particular country.
- 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_69f224de2bbc819081af6c32e1d857b9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69ffe12ee59c8190bc7da386e6d5332d |
completed | May 10, 2026, 1:36 a.m. |
| PD | Predicate disambiguation | batch_69ffe0a138bc8190a3d4b48cd579e985 |
completed | May 10, 2026, 1:34 a.m. |
Created at: April 29, 2026, 9:13 p.m.