Triple
T33988024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivien Harmon |
E871462
|
entity |
| Predicate | buysProperty |
P86552
|
FINISHED |
| Object | Murder House |
—
|
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: Murder House | Statement: [Vivien Harmon, buysProperty, Murder House]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buysProperty Context triple: [Vivien Harmon, buysProperty, Murder House]
-
A.
acquiredPropertyFrom
Indicates that one entity obtained ownership or control of a property or asset from another entity.
-
B.
squareProperty
Indicates that one entity is the square (second power) of a numerical property or value associated with another entity.
-
C.
buyIn
Indicates that one party purchases or acquires an ownership stake, participation, or commitment in something initiated or owned by another party.
-
D.
buys
chosen
Indicates that one entity purchases or acquires something from another entity, typically in exchange for money or other compensation.
-
E.
builtProperty
Indicates that a constructed structure or building has been created on, or is associated with, a particular property or piece of land.
- 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_69f3499e964c8190b674b03f6f791b4b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7039045e88190b268522ba43a9cf5 |
completed | May 3, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f70101ba1c819099380274e6df9a4d |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.