Triple
T29448690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene Adler |
E746920
|
entity |
| Predicate | relationshipWithSherlockHolmes |
P110508
|
FINISHED |
| Object | mutual respect |
—
|
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: mutual respect | Statement: [Irene Adler, relationshipWithSherlockHolmes, mutual respect]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithSherlockHolmes Context triple: [Irene Adler, relationshipWithSherlockHolmes, mutual respect]
-
A.
relationshipWithSherlock
chosen
Indicates that an entity has a specified type of personal or professional relationship with Sherlock.
-
B.
relationshipToDrWatson
Indicates the specific personal or professional relationship an entity has with Dr. Watson.
-
C.
roleInSherlock
Indicates the specific role or character that an entity portrays or holds in the context of the Sherlock series or franchise.
-
D.
describedBySherlockHolmesAs
Indicates that one entity is characterized or depicted in a particular way by Sherlock Holmes.
-
E.
relationshipToEleanorVance
Indicates the specific nature or type of relationship an entity has with Eleanor Vance.
- 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_69f0a7a230488190b44a97fe3d16f731 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_6a013c50bcb8819086d163f1a796a9b8 |
completed | May 11, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_6a013c01bac88190b15c70910c02a8a7 |
completed | May 11, 2026, 2:16 a.m. |
Created at: April 28, 2026, 3:30 p.m.