Triple
T26527371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latin Emperor of Constantinople |
E670727
|
entity |
| Predicate | lostCapitalIn |
P29466
|
FINISHED |
| Object | 1261 reconquest of Constantinople |
—
|
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: 1261 reconquest of Constantinople | Statement: [Latin Emperor of Constantinople, lostCapitalIn, 1261 reconquest of Constantinople]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lostCapitalIn Context triple: [Latin Emperor of Constantinople, lostCapitalIn, 1261 reconquest of Constantinople]
-
A.
lostCapitalTo
chosen
Indicates that one entity ceased to be the capital in favor of another entity, to which the capital status was transferred or lost.
-
B.
lostTerritoryBy
Indicates that one entity has had control or ownership of a territory taken away by another entity.
-
C.
lostCapital
Indicates that an entity has ceased to be the capital of a political or administrative region.
-
D.
lostSettlement
Indicates that a settlement previously possessed by an entity has been relinquished or is no longer under that entity’s control.
-
E.
capital
Indicates that one place serves as the official seat of government or primary administrative center for another political 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_69eeb31ea1e08190b9ff43cf9bc25bf8 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f613f41ccc8190b8bcc027ba1d0b93 |
completed | May 2, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:33 a.m.