Triple
T36187754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randyll Tarly |
E1046893
|
entity |
| Predicate | sideInLootTrainBattle |
P59829
|
FINISHED |
| Object | Lannister-Tarly host |
—
|
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: Lannister-Tarly host | Statement: [Randyll Tarly, sideInLootTrainBattle, Lannister-Tarly host]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sideInLootTrainBattle Context triple: [Randyll Tarly, sideInLootTrainBattle, Lannister-Tarly host]
-
A.
positionInTrain
Indicates the relative location or ordering of an entity within the sequence of cars or sections that make up a train.
-
B.
usedInBattle
Indicates that something (typically a tool, strategy, or resource) was employed or applied during a battle or combat situation.
-
C.
positionInBattle
Indicates the specific role or placement an entity occupies within the formation or structure of a battle.
-
D.
trainsPerSide
Indicates the number of trains allocated or operating on each side (e.g., direction, platform, or segment) within a system or configuration.
-
E.
hasCombatantSide
chosen
Indicates a relationship where a conflict, battle, or war is associated with one of the participating sides or factions involved in the combat.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b69b333081909cadbed3fcb8ecf5 |
completed | May 3, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c2a5f8819094ad4621d7b97e0c |
completed | May 3, 2026, 8:49 p.m. |
Created at: May 3, 2026, 4:08 p.m.