Triple
T26211368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golden Cap |
E655498
|
entity |
| Predicate | numberOfUsesPerOwner |
P156641
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [Golden Cap, numberOfUsesPerOwner, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfUsesPerOwner Context triple: [Golden Cap, numberOfUsesPerOwner, 3]
-
A.
hasNumberOfUses
chosen
Indicates the quantity of times something can be or is intended to be used.
-
B.
areUsedSince
Indicates that entities have been in use continuously starting from a specified point in time.
-
C.
typicalUseDays
Indicates the usual or expected number of days over which something is used or intended to be used.
-
D.
continuouslyUsedAs
Indicates that one entity is persistently and repeatedly employed or utilized as another entity or for a particular function over an extended, uninterrupted period.
-
E.
canBeUsedOncePer
Indicates that the associated action or resource is limited to a single use within each specified unit (such as per turn, per day, or per user).
- 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 26, 2026, 8:52 p.m.