Triple
T29742461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Ayn Shams |
E752647
|
entity |
| Predicate | opponentTypeSide2 |
P135487
|
FINISHED |
| Object | Byzantine regular troops |
—
|
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 regular troops | Statement: [Battle of Ayn Shams, opponentTypeSide2, Byzantine regular troops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentTypeSide2 Context triple: [Battle of Ayn Shams, opponentTypeSide2, Byzantine regular troops]
-
A.
secondaryOpponent
Indicates that an entity serves as an additional or backup opponent to a primary one in a given context or interaction.
-
B.
opponentCommanderSide
Indicates that one commander is positioned on the opposing side relative to another commander in a conflict or competitive scenario.
-
C.
opposedLeaderSide2
chosen
Indicates that the second leader or side is in opposition to another leader or side in a conflict or contest.
-
D.
opponentInCase
Indicates that two parties are on opposing sides in the same legal case or proceeding.
-
E.
opponentInScenario
Indicates that one entity is an adversary or rival of another within a specific scenario, context, or situation.
- 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_69f0d62b064081908c1ae61cd68fb139 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ed5d008190831cf8e44cce28af |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 28, 2026, 7:48 p.m.