Triple
T35077575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bagler faction |
E1012345
|
entity |
| Predicate | usedClaimants |
P28688
|
FINISHED |
| Object | royal pretenders |
—
|
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: royal pretenders | Statement: [Bagler faction, usedClaimants, royal pretenders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedClaimants Context triple: [Bagler faction, usedClaimants, royal pretenders]
-
A.
numberOfClaimants
Indicates the quantity of individuals or parties making a claim in a given context or case.
-
B.
claimantsInclude
chosen
Indicates that the specified set or group of claimants contains, as members, the entities referenced.
-
C.
supportedClaimant
Indicates that one entity has provided assistance, backing, or advocacy in favor of another entity who is making a claim or seeking a benefit.
-
D.
modernClaimant
Indicates that an entity is a present-day or contemporary holder or asserter of a particular title, right, or claim.
-
E.
usedToClaim
Indicates that something is employed as evidence, justification, or support in making a particular claim.
- 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_69f76dd32c008190853aef6028f60208 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7865d9dcc81909deaf635acd9ef56 |
completed | May 3, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69f78418fdf0819090420479783c7d47 |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.