Triple
T14180561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inner Guard |
E351439
|
entity |
| Predicate | worksWith |
P398
|
FINISHED |
| Object | Junior Deacon |
E35468
|
NE 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: Junior Deacon | Statement: [Inner Guard, worksWith, Junior Deacon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Junior Deacon Context triple: [Inner Guard, worksWith, Junior Deacon]
-
A.
Junior Deacon
chosen
The Junior Deacon is a Masonic lodge officer responsible for assisting in ceremonial duties and controlling access to the lodge during meetings.
-
B.
Mitch McDeere
Mitch McDeere is an ambitious young Harvard-educated lawyer who becomes entangled in a corrupt law firm’s criminal activities in John Grisham’s legal thriller "The Firm."
-
C.
Jack Deerson
Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
-
D.
Alden Brewster
Alden Brewster is the father of actress Jordana Brewster, known for her roles in the "Fast & Furious" film franchise.
-
E.
Henry Deacon
Henry Deacon is a brilliant and resourceful engineer and scientist in the science-fiction television series "Eureka," known for solving the town’s complex technical problems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61ca3ad88190944850c97760dcbf |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd19413bd08190930767abc2c588d4 |
completed | May 7, 2026, 10:59 p.m. |
Created at: April 10, 2026, 1:02 a.m.