Triple
T23351374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh the Great |
E592919
|
entity |
| Predicate | laterSupportedKing |
P137316
|
FINISHED |
| Object | Louis IV of France |
—
|
NE NERFINISHED |
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: Louis IV of France | Statement: [Hugh the Great, laterSupportedKing, Louis IV of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterSupportedKing Context triple: [Hugh the Great, laterSupportedKing, Louis IV of France]
-
A.
laterSupportedEmperor
Indicates that an entity provided support to an emperor at a later time or stage, rather than during the emperor’s initial rise or earlier period.
-
B.
alsoKingOf
Indicates that an entity who is king of one place is simultaneously king of another place as well.
-
C.
reignSupportedBy
chosen
Indicates that a ruler’s period of rule is backed, upheld, or sustained by a particular person, group, or power.
-
D.
servedKing
Indicates that one entity performed duties or services in allegiance or obedience to a king.
-
E.
successorAsTitularKing
Indicates that one entity becomes the next holder of a ceremonial or nominal kingship position previously held by 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19a1401748190b77df0a45c2aeebf |
completed | April 29, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69effcfd8d288190937a887fe6023c11 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:20 p.m.