Triple
T3124620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Foley |
E65266
|
entity |
| Predicate | roleInBattleOfTheNile |
P28183
|
FINISHED |
| Object | led vanguard ships through French line |
—
|
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: led vanguard ships through French line | Statement: [Thomas Foley, roleInBattleOfTheNile, led vanguard ships through French line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBattleOfTheNile Context triple: [Thomas Foley, roleInBattleOfTheNile, led vanguard ships through French line]
-
A.
opponentAtBattleOfTheNile
Indicates that one entity was an opposing combatant of the other in the Battle of the Nile.
-
B.
MamlukCommander
Indicates that an entity serves as a military commander within the Mamluk political or military structure in relation to another entity or context.
-
C.
notableBattleRole
chosen
Indicates the specific role or function an entity played in a notable or historically significant battle.
-
D.
opponentInBattleOfTheRiverPlate
Indicates that two entities were opposing sides facing each other in the Battle of the River Plate.
-
E.
joinsNile
Indicates that one river or watercourse flows into and becomes part of the Nile River.
- 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_69ad8580c72481909672d37acf647893 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada52d856c8190a5d65b8a6452be21 |
completed | March 8, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69ad9df62e548190b053e1478deed467 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:04 p.m.