Triple
T14071186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Achimota School |
E338609
|
entity |
| Predicate | hasHeadmistress |
P31330
|
FINISHED |
| Object | current head may change over time |
—
|
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: current head may change over time | Statement: [Achimota School, hasHeadmistress, current head may change over time]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeadmistress Context triple: [Achimota School, hasHeadmistress, current head may change over time]
-
A.
headOfSchool
chosen
Indicates that one entity serves as the principal leader or top administrator in charge of a school.
-
B.
hasNotableHeadmaster
Indicates that an institution or organization is associated with a headmaster who is particularly distinguished or noteworthy.
-
C.
relationshipToHeadmaster
Indicates the specific type of personal or professional relationship an entity has with the headmaster.
-
D.
hasHeadhouse
Indicates that one structure (typically a station or facility) includes or is associated with a headhouse building that serves as its main entrance or service area.
-
E.
successorSchoolHead
Indicates that one person becomes the next head (e.g., principal, headmaster) of a school after another person.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5aa828819098ef55a70a0decbc |
completed | April 14, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.