Triple
T22774888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lions |
E563666
|
entity |
| Predicate | governingBodyTitle |
P18747
|
FINISHED |
| Object | Director of Athletics |
—
|
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: Director of Athletics | Statement: [Lions, governingBodyTitle, Director of Athletics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governingBodyTitle Context triple: [Lions, governingBodyTitle, Director of Athletics]
-
A.
governingBody2
Indicates that an entity serves as the official authority or administrative body responsible for overseeing, managing, or regulating another entity.
-
B.
governingHeadTitle
chosen
Indicates the official title held by the person who serves as the governing head of an entity (such as a country, organization, or institution).
-
C.
governingBodyOfType
Indicates that an entity serves as the official governing body for another entity of a specified type or category.
-
D.
governingBodyExample
Indicates that the subject entity serves as an example or instance of a governing body for the object entity.
-
E.
governingBodyNow
Indicates that the specified entity currently serves as the official governing authority or administrative body of another entity.
- 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_69e24554497c819080b996e071de27c2 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17b60eec48190b0aaf3eb7ede38d4 |
completed | April 29, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:28 p.m.