Triple
T29683433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sick Boy |
E751017
|
entity |
| Predicate | relationshipTypeWithRenton |
P10690
|
FINISHED |
| Object | friend and rival |
—
|
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: friend and rival | Statement: [Sick Boy, relationshipTypeWithRenton, friend and rival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithRenton Context triple: [Sick Boy, relationshipTypeWithRenton, friend and rival]
-
A.
alsoTenant
Indicates that two or more entities share the status of being tenants, typically occupying the same property or rental arrangement.
-
B.
typeOfEstateConnection
Indicates the specific kind of estate-related relationship or connection that exists between two entities.
-
C.
relationshipBetweenHouses
Indicates a relational connection or association that exists between two or more houses.
-
D.
relationToMLS
Indicates a relationship or association that an entity has with a specific MLS (Multiple Listing Service) system or record.
-
E.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
- 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_69f0d625b09481909b0b69aea1e846c8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a01926e2f348190a632eff5c91db5e0 |
completed | May 11, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_6a01923488f4819094d79a27f4bc8ab8 |
completed | May 11, 2026, 8:24 a.m. |
Created at: April 28, 2026, 7:11 p.m.