Triple
T4257656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saybrook College |
E96017
|
entity |
| Predicate | hasHeadTitleCurrent |
P10091
|
FINISHED |
| Object | Head of College |
—
|
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: Head of College | Statement: [Saybrook College, hasHeadTitleCurrent, Head of College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeadTitleCurrent Context triple: [Saybrook College, hasHeadTitleCurrent, Head of College]
-
A.
currentHeadTitle
chosen
Indicates the official title or position currently held by the head or leader of an entity.
-
B.
hasHeading
Indicates that one entity serves as a heading or title for another entity.
-
C.
hasTitleType
Indicates that an entity holds a specific kind or category of title (such as job title, honorific, or formal designation).
-
D.
hasTitleHolder
Indicates that one entity is the current or designated holder of a specific title, position, or honor associated with another entity.
-
E.
hasTitleLocation
Indicates that an entity’s title or heading is associated with a specific location or position (e.g., in a document, interface, or spatial layout).
- 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_69b3454095ac81909c2494f7ff294af1 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ec321008190b2cc1aca6ab690c4 |
completed | March 12, 2026, 11:39 p.m. |
| PD | Predicate disambiguation | batch_69b347f73e008190a908a48ef389945a |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:06 p.m.