Triple
T10200899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narsil |
E238877
|
entity |
| Predicate | statusBeforeReforging |
P92684
|
FINISHED |
| Object | broken sword |
—
|
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: broken sword | Statement: [Narsil, statusBeforeReforging, broken sword]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusBeforeReforging Context triple: [Narsil, statusBeforeReforging, broken sword]
-
A.
formerSpireStatus
Indicates that an entity previously held a particular status or role within a spire but no longer does.
-
B.
energyBeforeUpgrade
Indicates the amount or state of energy associated with an entity prior to a specified upgrade or improvement action.
-
C.
wasUpgradedFor
Indicates that one entity was improved, enhanced, or updated specifically to serve, benefit, or be compatible with another entity.
-
D.
stateBeforeFormation
Indicates a relationship where one state or condition existed prior to the formation or creation of another entity or state.
-
E.
refurbishedIn
Indicates that an entity has undergone restoration, repair, or renovation at a specific time or during a particular period.
- F. None of above. chosen
Provenance (4 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_69ca84e1ea088190b38162e43d4cfa8f |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdee40cb7481908a1bf4d5636eb8ef |
completed | April 2, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69cd7c8b7f348190a585daa70de4d4c8 |
completed | April 1, 2026, 8:14 p.m. |
| PDg | Predicate description generation | batch_69cd7edc6cf081909d95859d880a4059 |
completed | April 1, 2026, 8:23 p.m. |
Created at: March 30, 2026, 9:14 p.m.