Triple
T28824554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flavia Caesariensis |
E727865
|
entity |
| Predicate | hasUncertainCapitalCandidates |
P82815
|
FINISHED |
| Object | Londinium |
—
|
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: Londinium | Statement: [Flavia Caesariensis, hasUncertainCapitalCandidates, Londinium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUncertainCapitalCandidates Context triple: [Flavia Caesariensis, hasUncertainCapitalCandidates, Londinium]
-
A.
hasUncertainCapital
chosen
Indicates that the capital city or administrative center associated with an entity is not known with certainty or is subject to doubt or dispute.
-
B.
hasUncertainNumber
Indicates that the associated quantity or count is not known precisely or cannot be determined with certainty.
-
C.
hasUncertainForm
Indicates that the form or structure of something is not clearly defined, fixed, or confidently known.
-
D.
hasUncertainOriginalName
Indicates that the entity’s original name is not known with certainty or is subject to doubt or ambiguity.
-
E.
hasUncertainty
Indicates that the relationship or value is associated with some level or type of uncertainty rather than being fully definite or precise.
- 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 28, 2026, 6:35 a.m.