Triple
T4035579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Behind a Mask |
E83818
|
entity |
| Predicate | isPseudonymousWork |
P3799
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Behind a Mask, isPseudonymousWork, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPseudonymousWork Context triple: [Behind a Mask, isPseudonymousWork, true]
-
A.
publishedAnonymously
Indicates that a work was made public without revealing the identity of its creator or author.
-
B.
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.
-
C.
isLesserKnownWork
Indicates that one work is relatively less famous, recognized, or widely known compared to other works (typically by the same creator or within the same domain).
-
D.
pseudonymCoinedBy
Indicates that a particular pseudonym was created or invented by a specific agent or source.
-
E.
isPosthumousWorkOf
Indicates that a work was created, published, or became known only after the death of the person with whom it is associated.
- 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_69aed92f7cf0819098e0539bdcc3767f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb132f6c8190937acd35a6a5a9e4 |
completed | March 9, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69aef8fe440c819093a7fa22c4ff3f1a |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:36 p.m.