Triple
T32455390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marian Rolf |
E829409
|
entity |
| Predicate | relationshipWithHouse |
P26313
|
FINISHED |
| Object | becomes obsessed with house |
—
|
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: becomes obsessed with house | Statement: [Marian Rolf, relationshipWithHouse, becomes obsessed with house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithHouse Context triple: [Marian Rolf, relationshipWithHouse, becomes obsessed with house]
-
A.
relationshipBetweenHouses
Indicates a relational connection or association that exists between two or more houses.
-
B.
bondedToHouse
Indicates a relationship where an entity is legally or contractually obligated, tied, or pledged in connection to a specific house.
-
C.
associatedHouse
chosen
Indicates a relationship where one entity is linked or connected to a particular house, typically as its related or corresponding house.
-
D.
relationToMLS
Indicates a relationship or association that an entity has with a specific MLS (Multiple Listing Service) system or record.
-
E.
relationshipToHost
Indicates the type or nature of the connection, association, or role that one entity has in relation to a host entity.
- 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_69f3491df9288190afc0b23b1d6e72ce |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379edf2d88190b492fca86ed23cac |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:56 a.m.