Triple
T29488571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gordon Lyon |
E748001
|
entity |
| Predicate | usesPseudonymFor |
P3799
|
FINISHED |
| Object | security research publications |
—
|
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: security research publications | Statement: [Gordon Lyon, usesPseudonymFor, security research publications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesPseudonymFor Context triple: [Gordon Lyon, usesPseudonymFor, security research publications]
-
A.
usedPseudonym
chosen
Indicates that an entity performed an action or participated in a context under a name that was not their real or primary identity.
-
B.
usedPseudonymWith
Indicates that one entity employed a pseudonym or alias when interacting or being associated with another entity.
-
C.
revealedAsPseudonymIn
Indicates that one identity or name is disclosed or recognized as a pseudonym within a particular context, work, or source.
-
D.
coAppearsWithPseudonym
Indicates that an entity appears together with another entity that is identified or referenced by a pseudonym in the same context or source.
-
E.
addresseePseudonym
Indicates that the referenced name is a pseudonym used for the addressee in the context of the described communication or interaction.
- 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_69f0bd43ba30819095eb1cfc3adf525c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f7117e55908190a67105e92bc4830f |
completed | May 3, 2026, 9:12 a.m. |
| PD | Predicate disambiguation | batch_69f70f380690819090cc34763ba460ed |
completed | May 3, 2026, 9:02 a.m. |
Created at: April 28, 2026, 4:11 p.m.