Triple
T1695384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seymour Papert |
E36644
|
entity |
| Predicate | mentored |
P12723
|
FINISHED |
| Object | Mitchel Resnick |
E38207
|
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: Mitchel Resnick | Statement: [Seymour Papert, mentored, Mitchel Resnick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mitchel Resnick Context triple: [Seymour Papert, mentored, Mitchel Resnick]
-
A.
Mitchel Resnick
chosen
Mitchel Resnick is an American educator and MIT professor known for his pioneering work in constructionist learning and for leading the development of the Scratch programming language for children.
-
B.
Walter Bender
Walter Bender is an American software engineer and open-source advocate best known for his leadership in educational technology initiatives, including co-founding the One Laptop per Child project and developing child-focused learning software.
-
C.
Seymour Papert
Seymour Papert was a pioneering mathematician, computer scientist, and educator best known for co-inventing the Logo programming language and advancing constructionist learning theories in education technology.
-
D.
Hal Abelson
Hal Abelson is an American computer scientist and MIT professor known for his pioneering work in computer science education, open knowledge, and software freedom.
-
E.
Andrea diSessa
Andrea diSessa is an American educational researcher and cognitive scientist known for his work on physics education, computational literacy, and the design of learning environments.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentored Context triple: [Seymour Papert, mentored, Mitchel Resnick]
-
A.
guidedBy
chosen
Indicates that an entity’s actions, decisions, or movement are directed, advised, or led by another entity.
-
B.
coachedAlongside
Indicates that two or more individuals served as coaches at the same time, typically for the same team, organization, or event.
-
C.
guru
Indicates that one entity serves as a spiritual teacher, guide, or mentor to another entity.
-
D.
facilitatedBy
Indicates that an action, process, or relationship occurs or is made easier through the assistance, support, or enabling role of a particular agent or mechanism.
-
E.
managedTo
Indicates that an entity successfully accomplished or achieved a particular action or outcome, often despite difficulty or obstacles.
- F. None of above.
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_69a886163dec8190859c514232a37a05 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf169da888190b3aa334752f1952b |
completed | March 6, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad8ac9ed2c81909fe3fe40515526de |
completed | March 8, 2026, 2:42 p.m. |
| PD | Predicate disambiguation | batch_69aa61b8ce348190b46154af0b041ff0 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.