Triple
T22446673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Abramov |
E554878
|
entity |
| Predicate | twitterProfile |
P2866
|
FINISHED |
| Object | https://twitter.com/dan_abramov |
—
|
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: https://twitter.com/dan_abramov | Statement: [Dan Abramov, twitterProfile, https://twitter.com/dan_abramov]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: twitterProfile Context triple: [Dan Abramov, twitterProfile, https://twitter.com/dan_abramov]
-
A.
twitterUsername
Indicates that one entity is the Twitter handle or username associated with another entity.
-
B.
twitterHandle
chosen
Indicates that one entity is the Twitter username or account identifier associated with another entity.
-
C.
screenName
Indicates the display or handle name associated with an entity, typically used as its visible identifier in user interfaces or social platforms.
-
D.
publicProfile
Indicates that an entity’s profile or identifying information is visible and accessible to the general public.
-
E.
mediaProfile
Indicates a relationship where a media-related profile or account is associated with an entity, typically representing its presence or identity in media contexts.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4803908190990280ebd258cb03 |
completed | April 29, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.