Triple
T32932938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Secret of the Old Mill |
E842444
|
entity |
| Predicate | hasProtagonistDuo |
P188096
|
FINISHED |
| Object | Frank and Joe Hardy |
—
|
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: Frank and Joe Hardy | Statement: [The Secret of the Old Mill, hasProtagonistDuo, Frank and Joe Hardy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtagonistDuo Context triple: [The Secret of the Old Mill, hasProtagonistDuo, Frank and Joe Hardy]
-
A.
hasSecondaryProtagonist
Indicates that an entity (such as a work of fiction) features another character who serves as a secondary or supporting main protagonist alongside the primary one.
-
B.
hasSecondaryProtagonistOccupation
Indicates that a secondary protagonist in a narrative has a specific occupation or job role.
-
C.
hasSiblingProtagonists
chosen
Indicates that the work features two or more protagonists who are siblings to each other.
-
D.
isPerformedByDuo
Indicates that an action or event is carried out jointly by two participants acting together as a duo.
-
E.
hasTwinActors
Indicates that two or more actors share a twin relationship, typically portraying twin characters or being treated as twins within a given context.
- 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_69f34948adfc8190a937f1f622783c0b |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a01378bf05c8190af9f5e06a2810c7d |
completed | May 11, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_6a0137277c6c8190bcec341f2a0757c4 |
completed | May 11, 2026, 1:55 a.m. |
Created at: May 1, 2026, 1:20 a.m.