Triple
T18399851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dyumatsena |
E449962
|
entity |
| Predicate | regains |
P3243
|
FINISHED |
| Object | kingdom |
—
|
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: kingdom | Statement: [Dyumatsena, regains, kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regains Context triple: [Dyumatsena, regains, kingdom]
-
A.
regainedPowerAgainIn
Indicates that an entity, having previously lost power, has once more returned to a position of power or control within a specified context or location.
-
B.
regainedPowerIn
chosen
Indicates that an entity has recovered or reestablished its previous level of power, control, or authority within a specified context or domain.
-
C.
regainedSpeech
Indicates that an entity has recovered the ability to speak after having previously lost it.
-
D.
regainedTitleFrom
Indicates that an entity has recovered a previously held title or position from another entity who had taken or held it in the interim.
-
E.
regenerationOf
Indicates that one entity is the renewed, restored, or regrown version of another entity, typically after damage, loss, or degradation.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e518499b1481909c5de786c48faeba |
completed | April 19, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69e44ff1f92c8190afbb8e85d12bf2a9 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:46 a.m.