Triple
T8893763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of the City Register |
E211749
|
entity |
| Predicate | recordsFor |
P72845
|
FINISHED |
| Object | residential properties |
—
|
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: residential properties | Statement: [Office of the City Register, recordsFor, residential properties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordsFor Context triple: [Office of the City Register, recordsFor, residential properties]
-
A.
recordsType
Indicates that one entity documents, stores, or keeps an official account of a particular type or category of information, event, or item.
-
B.
recordDetail
Indicates that one entity stores or documents specific information or attributes about another entity.
-
C.
recordKeeper
chosen
Indicates a relationship where one entity is responsible for maintaining, managing, or preserving official records or documented information about another entity or activity.
-
D.
poweredRecord
Indicates that one entity functions as a powered or electrified version of another entity, typically enabling enhanced or active operation.
-
E.
recordsOnAppeal
Indicates that certain records or documents are included in, or pertain to, the official record for an appeal in a legal or administrative proceeding.
- 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_69ca83907954819096d52a245b635841 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61bc92c881908aab536af9b35178 |
completed | April 1, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2aec04819093c932fe51c0f08d |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:54 p.m.