Triple
T29761234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Fire of 1834 |
E753773
|
entity |
| Predicate | fireOrigin |
P56348
|
FINISHED |
| Object | House of Lords basement |
—
|
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: House of Lords basement | Statement: [Great Fire of 1834, fireOrigin, House of Lords basement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fireOrigin Context triple: [Great Fire of 1834, fireOrigin, House of Lords basement]
-
A.
fireBeganAt
chosen
Indicates that the event of a fire starting occurred at a specific time or location.
-
B.
fireOccurred
Indicates that a fire event took place at a specific time and/or location.
-
C.
fireType
Indicates that one entity has a specific classification or category related to fire (e.g., type, kind, or nature of fire).
-
D.
fireIncidentRelated
Indicates that there is a connection or association between a specific fire incident and another entity, event, or record.
-
E.
fireSpreadTo
Indicates that a fire originating in one location has extended and begun burning in another specified location.
- 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_69f0ef827ff88190ade56e0b0846b713 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f673d041448190a414a19cf28b09d2 |
completed | May 2, 2026, 9:59 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 8:33 p.m.