Triple
T30151726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foundation of Constantinople |
E766413
|
entity |
| Predicate | hasPredecessorCity |
P16664
|
FINISHED |
| Object | Byzantium |
—
|
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: Byzantium | Statement: [Foundation of Constantinople, hasPredecessorCity, Byzantium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPredecessorCity Context triple: [Foundation of Constantinople, hasPredecessorCity, Byzantium]
-
A.
hasPredecessorNameInCity
Indicates that an entity has a predecessor (e.g., an earlier version or prior holder) that had the same name in a specified city.
-
B.
predecessorCityName
Indicates that the value is the name of the city that previously held a given role, status, or position before the current city.
-
C.
hasCitySuccessor
Indicates that one city is the successor or replacement of another city, typically in terms of status, function, or administrative role.
-
D.
previousCity
chosen
Indicates that one city was the immediately preceding location visited or lived in before another city.
-
E.
hasCityServedSuccessor
Indicates that one city served by a service, role, or entity is the successor to another previously served city in that same context.
- 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_69f22479cd088190ab4c6f3fce39d1c5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ffbf84f4948190b41a7bba07ae61ec |
completed | May 9, 2026, 11:13 p.m. |
| PD | Predicate disambiguation | batch_69ffbf0a59f88190870dbe25d8a63a00 |
completed | May 9, 2026, 11:11 p.m. |
Created at: April 29, 2026, 7:20 p.m.