Triple
T23309405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Glixman |
E590538
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Masque |
—
|
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: Masque | Statement: [Jeff Glixman, workedOn, Masque]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Masque Context triple: [Jeff Glixman, workedOn, Masque]
-
A.
Masques
chosen
Masques is a creative work associated with Brand X, likely recognized as one of the brand’s signature or standout projects.
-
B.
MASQUE
MASQUE is an IETF protocol framework that enables proxying of network traffic such as HTTP, DNS, and VPN-like tunnels over HTTP/3 using QUIC.
-
C.
Máscaras
Máscaras is a Brazilian telenovela known for its themes of identity, intrigue, and deception.
-
D.
Le maschere
Le maschere is a comic opera in three acts by Italian composer Pietro Mascagni that playfully revives the traditions and stock characters of commedia dell’arte.
-
E.
House of the Masks
House of the Masks is an ancient residential building on the Greek island of Delos, notable for its well-preserved mosaics depicting theatrical masks.
- 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19729f7a4819092a1d24415b3df7a |
completed | April 29, 2026, 5:29 a.m. |
Created at: April 17, 2026, 5:05 p.m.