Triple
T27338936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyme, New Hampshire |
E690036
|
entity |
| Predicate | highSchoolStudentsOftenAttend |
P33910
|
FINISHED |
| Object | Hanover High School |
—
|
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: Hanover High School | Statement: [Lyme, New Hampshire, highSchoolStudentsOftenAttend, Hanover High School]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highSchoolStudentsOftenAttend Context triple: [Lyme, New Hampshire, highSchoolStudentsOftenAttend, Hanover High School]
-
A.
highSchoolForMostStudents
chosen
Indicates that the referenced school is the primary high school attended by the majority of students in a given group or area.
-
B.
highSchoolSetting
Indicates that an event, interaction, or situation takes place within the context or environment of a high school.
-
C.
attendedHighSchoolIn
Indicates that an entity completed or was enrolled in high school education in a specified location.
-
D.
servesHighSchool
Indicates that an entity provides services, support, or resources specifically to a high school.
-
E.
highSchoolStatus
Indicates the relationship between a person and their current or completed status in high school (e.g., enrolled, graduated, dropped out).
- 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_69ef355e5b388190a8fc1eba9b4a6656 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62ad17d30819082fd2c9dbc1f964f |
completed | May 2, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:41 a.m.