Triple
T37662957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caves & Cliffs: Part I |
E937755
|
entity |
| Predicate | addsItem |
P186932
|
FINISHED |
| Object | spyglass |
—
|
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: spyglass | Statement: [Caves & Cliffs: Part I, addsItem, spyglass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addsItem Context triple: [Caves & Cliffs: Part I, addsItem, spyglass]
-
A.
addsUnit
Indicates that one entity increases another by contributing an additional unit or component to it.
-
B.
canBeAddedTo
Indicates that one entity is capable of being combined or incorporated with another entity, typically without conflict or incompatibility.
-
C.
addsNewGear
chosen
Indicates that an entity introduces or incorporates additional gear into an existing set, system, or configuration.
-
D.
leavesItem
Indicates that an entity departs from or moves away from another entity, relinquishing or no longer retaining it.
-
E.
addedFor
Indicates that one entity was created, included, or introduced specifically for the benefit, use, or purpose of another entity.
- 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.