Triple
T37515107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Templar |
E932613
|
entity |
| Predicate | startingWeaponSpecialization |
P131403
|
FINISHED |
| Object | staves |
—
|
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: staves | Statement: [Templar, startingWeaponSpecialization, staves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingWeaponSpecialization Context triple: [Templar, startingWeaponSpecialization, staves]
-
A.
mainCharacterSpecialization
Indicates the specific role, class, or area of expertise that the main character is focused on or specialized in.
-
B.
weaponProficiency
chosen
Indicates that an entity has the skill or qualification to effectively use a specified weapon.
-
C.
specialWeapon
Indicates that an entity is a weapon with unique, enhanced, or otherwise exceptional properties compared to standard weapons.
-
D.
weaponDiscipline
Indicates that an entity practices, adheres to, or is governed by a particular system, style, or code of weapon use or combat training.
-
E.
teachesWeapon
Indicates that one entity instructs or trains another entity in the use or knowledge of a specific weapon.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0117b6539c8190be7d231e891fe546 |
completed | May 10, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_6a011762f7ec8190afc884b92419d33f |
completed | May 10, 2026, 11:40 p.m. |
Created at: May 3, 2026, 4:17 p.m.