Triple
T32936143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Many, Louisiana |
E842531
|
entity |
| Predicate | hasLocalSchoolSystem |
P85311
|
FINISHED |
| Object |
Sabine Parish School Board
Sabine Parish School Board is the public school district responsible for overseeing and operating the public schools in Sabine Parish, Louisiana.
|
E2029921
|
NE FINISHED |
How this triple was built (3 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: Sabine Parish School Board | Statement: [Many, Louisiana, hasLocalSchoolSystem, Sabine Parish School Board]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sabine Parish School Board Triple: [Many, Louisiana, hasLocalSchoolSystem, Sabine Parish School Board]
Generated description
Sabine Parish School Board is the public school district responsible for overseeing and operating the public schools in Sabine Parish, Louisiana.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalSchoolSystem Context triple: [Many, Louisiana, hasLocalSchoolSystem, Sabine Parish School Board]
-
A.
hasLocalElementarySchools
Indicates that a place or area contains or is served by one or more elementary-level schools located within or very near its boundaries.
-
B.
hasSchoolDistricts
chosen
Indicates that one entity administers, contains, or is associated with one or more school districts.
-
C.
hasRegionalSchool
Indicates that an entity has an associated school that serves or operates within a specific geographic region.
-
D.
hasSchoolSystemLevel
Indicates that an educational institution is associated with a particular level or tier within a school system (e.g., primary, secondary, tertiary).
-
E.
hasParochialSchool
Indicates that an entity operates, is associated with, or includes a parochial (religious-affiliated) school.
- F. None of above.
Provenance (6 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_69f34949727c81909d195c97de3341c8 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe5d58c3e48190910aa3c23485e2c4 |
completed | May 8, 2026, 10:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a34d2675e288190a6ab90d0947c4758 |
completed | June 19, 2026, 5:23 a.m. |
| NEDg | Description generation | batch_6a34d35803148190815cb96805ce4ba0 |
completed | June 19, 2026, 5:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a34d423fc108190aeb3f93fbabdf591 |
completed | June 19, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69fe5c92090c8190bcfa412c0a3619df |
completed | May 8, 2026, 9:58 p.m. |
Created at: May 1, 2026, 1:20 a.m.