Triple
T16385939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Ongal |
E397921
|
entity |
| Predicate | primaryOpponentRulerTitle |
P68489
|
FINISHED |
| Object | Byzantine emperor |
—
|
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: Byzantine emperor | Statement: [Battle of Ongal, primaryOpponentRulerTitle, Byzantine emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryOpponentRulerTitle Context triple: [Battle of Ongal, primaryOpponentRulerTitle, Byzantine emperor]
-
A.
opponentMonarch
Indicates that one monarch stands in an opposing or adversarial position to another monarch, typically in conflict or competition.
-
B.
laterRulerTitle
Indicates that an entity held a particular ruler title at a later point in time, after some earlier status or title.
-
C.
rulerOf
Indicates that one entity holds governing authority or sovereignty over another entity, such as a person ruling a country or territory.
-
D.
opponentTitle
chosen
Indicates that the object is the formal title or designation held by an opponent in a competitive or adversarial context.
-
E.
traditionalTitleOfLeader
Indicates the customary or historically recognized title used to refer to a particular leader.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e3263d260081909db9ac6016d5738a |
completed | April 18, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69e226f94dd48190b7b8e0e983738a67 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:08 a.m.