Triple
T37661643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eye of Ender |
E937729
|
entity |
| Predicate | thrownTrajectory |
P137755
|
FINISHED |
| Object | toward nearest stronghold |
—
|
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: toward nearest stronghold | Statement: [Eye of Ender, thrownTrajectory, toward nearest stronghold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thrownTrajectory Context triple: [Eye of Ender, thrownTrajectory, toward nearest stronghold]
-
A.
thrownThrough
Indicates that one entity has been propelled with force so that it passes through another entity or barrier.
-
B.
wasThrownFrom
Indicates that an entity was propelled away or ejected from another entity, typically by a forceful or intentional throwing action.
-
C.
throws
Indicates that one entity propels or hurls another entity or object through space, typically by a deliberate physical action.
-
D.
throwingImplement
Indicates that an entity uses or propels an implement (such as a tool, weapon, or object) by throwing it.
-
E.
resultingTrajectory
chosen
Indicates the path or course that emerges as the outcome of a prior motion, interaction, or transformation.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaa1321b48190af92a3e7ec24ec5b |
completed | May 6, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69fba8860f98819080b7bab05837b974 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.