Triple
T37515132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadow (Path of Exile) |
E932614
|
entity |
| Predicate | weaponAffinity |
P121492
|
FINISHED |
| Object | claws |
—
|
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: claws | Statement: [Shadow (Path of Exile), weaponAffinity, claws]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponAffinity Context triple: [Shadow (Path of Exile), weaponAffinity, claws]
-
A.
weaponPreference
chosen
Indicates a relationship where an entity favors or typically uses a particular type of weapon over others.
-
B.
weaponDiscipline
Indicates that an entity practices, adheres to, or is governed by a particular system, style, or code of weapon use or combat training.
-
C.
weaponProficiency
Indicates that an entity has the skill or qualification to effectively use a specified weapon.
-
D.
associatedWithWeapon
Indicates that an entity has a connection or involvement with a weapon, such as ownership, use, presence, or relevance in a given context.
-
E.
dedicatedToWeapon
Indicates that something is specifically assigned, reserved, or purposed for use with a particular weapon or type of 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_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69fbbd13595c81908719f52c3d37a7e8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:17 p.m.