Triple
T3211555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dana Delany |
E67291
|
entity |
| Predicate | hasTwitterProfile |
P2866
|
FINISHED |
| Object | https://twitter.com/DanaDelany |
—
|
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/DanaDelany | Statement: [Dana Delany, hasTwitterProfile, https://twitter.com/DanaDelany]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTwitterProfile Context triple: [Dana Delany, hasTwitterProfile, https://twitter.com/DanaDelany]
-
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.
hasProfile
Indicates that an entity is associated with or possesses a specific profile representation or account.
-
D.
hasSocialIdentity
Indicates that an entity possesses or is associated with a particular social identity, such as a role, group membership, or socially recognized status.
-
E.
isPopularOnSocialMedia
Indicates that an entity is widely followed, frequently engaged with, or broadly recognized across social media platforms.
- 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_69ad858ac36c81909962589cd277d6e2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaaba224c8190ad2f4e0ed1c2ca4a |
completed | March 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69ad9e09b83881908801d79c3d9254f9 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:07 p.m.