Triple
T1325391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man in the Iron Mask |
E28314
|
entity |
| Predicate | allegedIdentity |
P16813
|
FINISHED |
| Object | twin brother of Louis XIV |
—
|
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: twin brother of Louis XIV | Statement: [Man in the Iron Mask, allegedIdentity, twin brother of Louis XIV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedIdentity Context triple: [Man in the Iron Mask, allegedIdentity, twin brother of Louis XIV]
-
A.
subjectIdentity
Indicates that two or more references correspond to the same underlying entity or individual identity.
-
B.
identityRevealedIn
Indicates that an entity’s true identity becomes known or disclosed within a specified context, source, or situation.
-
C.
hasIdentity
Indicates that one entity is the same as, or is identified as, another specific entity or identifier.
-
D.
hasDisputedIdentityWith
Indicates that two entities are associated with conflicting, uncertain, or contested identifications, such that their true or correct identities are in dispute relative to each other.
-
E.
allegedStatus
chosen
Indicates that a particular status or condition is claimed or asserted about an entity, but has not been confirmed as true.
- 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19fd2648190932a85eacb3e7ec4 |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beedb49c8190beb5b85cdda05013 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.