Triple
T2106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sally Kornbluth |
E38
|
entity |
| Predicate | hasRole |
P161
|
FINISHED |
| Object | chief executive of MIT |
—
|
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: chief executive of MIT | Statement: [Sally Kornbluth, hasRole, chief executive of MIT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRole Context triple: [Sally Kornbluth, hasRole, chief executive of MIT]
-
A.
hasMemberType
Indicates that an entity includes or is associated with members belonging to a specified type or category.
-
B.
hasRepresentationIn
Indicates that one entity is represented, depicted, or encoded within another entity, such as a concept, object, or data structure having a corresponding representation in a specific medium or context.
-
C.
hasPart
Indicates that one entity is a component, segment, or constituent part of another entity.
-
D.
eligibility
Indicates that an entity meets the required conditions or qualifications to participate in, receive, or perform something.
-
E.
hasLimitation
Indicates that an entity is subject to a constraint, restriction, or boundary that limits its scope, capability, or applicability.
- F. None of above. chosen
Provenance (4 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_69a22cde80848190b62c5f556b4d62ba |
completed | Feb. 27, 2026, 11:46 p.m. |
| NER | Named-entity recognition | batch_69a2316d88a08190b2e03041674b5674 |
completed | Feb. 28, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69a230c3ee4481908216244c38aa8aef |
completed | Feb. 28, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69a2316cbe58819096cc036d6e3b103c |
completed | Feb. 28, 2026, 12:06 a.m. |
Created at: Feb. 27, 2026, 11:48 p.m.