Triple
T2149246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eurasian Steppe |
E47140
|
entity |
| Predicate | weaponryInnovation |
P20686
|
FINISHED |
| Object | composite bow |
—
|
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: composite bow | Statement: [Eurasian Steppe, weaponryInnovation, composite bow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponryInnovation Context triple: [Eurasian Steppe, weaponryInnovation, composite bow]
-
A.
militaryInnovation
chosen
Indicates the introduction or development of new methods, technologies, or strategies within a military context.
-
B.
militaryTechnology
Indicates that one entity is a type of military-related technology used for defense, combat, or warfare purposes.
-
C.
militaryProject
Indicates a project that is conducted, funded, or controlled by a military organization, typically for defense, security, or warfare-related purposes.
-
D.
armamentWartime
Indicates a relationship where an entity serves as a weapon or military equipment used by another entity specifically in a wartime context.
-
E.
weaponsUsed
Indicates that one entity employed or utilized another entity as a weapon in carrying out an action or event.
- 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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbeaa14bc81908486683decd7ae42 |
completed | March 7, 2026, 5:59 a.m. |
| PD | Predicate disambiguation | batch_69abbd9846e88190b6c2941dd9ce7749 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.