Triple
T13831654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elementary |
E332411
|
entity |
| Predicate | characterizesSherlockHolmesAs |
P111674
|
FINISHED |
| Object | recovering drug addict |
—
|
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: recovering drug addict | Statement: [Elementary, characterizesSherlockHolmesAs, recovering drug addict]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterizesSherlockHolmesAs Context triple: [Elementary, characterizesSherlockHolmesAs, recovering drug addict]
-
A.
roleInSherlock
Indicates the specific role or character that an entity portrays or holds in the context of the Sherlock series or franchise.
-
B.
roleInMurderOnTheOrientExpress
Indicates the specific involvement or function an entity has within the context of the murder case in "Murder on the Orient Express."
-
C.
hasFictionalDetective
Indicates that one entity (typically a work or series) features or includes a fictional detective character as part of its content.
-
D.
workInSherlockHolmesCanon
Indicates that an entity is a work (e.g., story, novel, adaptation) that belongs to or is part of the Sherlock Holmes canon.
-
E.
relationshipWithSherlock
Indicates that an entity has a specified type of personal or professional relationship with Sherlock.
- F. None of above. chosen
Provenance (4 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0299334481908c2b271eaf06e4b7 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
| PDg | Predicate description generation | batch_69dcad0eea9881908f71e1eed9a2446b |
completed | April 13, 2026, 8:45 a.m. |
Created at: April 9, 2026, 10:13 p.m.