Triple
T21623364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Lakoff |
E533633
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Lakoff |
—
|
NE NERFINISHED |
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: Lakoff | Statement: [George Lakoff, familyName, Lakoff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lakoff Context triple: [George Lakoff, familyName, Lakoff]
-
A.
George Lakoff
chosen
George Lakoff is an American cognitive linguist known for his work on conceptual metaphor and the role of embodied cognition in shaping human thought and language.
-
B.
Leacock-Pennebaker
Leacock-Pennebaker was a pioneering American documentary film production company known for its influential cinéma vérité works in the 1960s.
-
C.
Words and Rules
Words and Rules is a book by cognitive scientist Steven Pinker that explores how the human mind processes language, particularly the interplay between memorized words and grammatical rules.
-
D.
Lesk
Lesk is a smaller river or stream in Poland that serves as a tributary of the Bóbr River.
-
E.
How to Do Things with Words
How to Do Things with Words is a foundational work in 20th-century philosophy of language by J. L. Austin that introduced speech act theory and transformed understandings of how language functions in practice.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef521125f481909ccfc95d884976e2 |
completed | April 27, 2026, 12:09 p.m. |
Created at: April 16, 2026, 6:34 p.m.