Triple
T36899125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | court of Theodosius II |
E911979
|
entity |
| Predicate | influentialOfficial |
P83171
|
FINISHED |
| Object | Pulcheria |
—
|
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: Pulcheria | Statement: [court of Theodosius II, influentialOfficial, Pulcheria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: influentialOfficial Context triple: [court of Theodosius II, influentialOfficial, Pulcheria]
-
A.
influentialAs
Indicates that one entity has at least as much influence or impact as another entity.
-
B.
influentialFrom
Indicates that one entity has exerted influence on another, contributing to or shaping the latter’s ideas, behavior, or development.
-
C.
influentialMember
chosen
Indicates that an entity plays a significant, impactful, or leading role within a group, organization, or community.
-
D.
influentialLeader
Indicates that an entity holds a leadership role that significantly shapes, guides, or impacts the actions, opinions, or outcomes of others.
-
E.
influenceOf
Indicates that one entity affects, shapes, or alters the state, behavior, or properties of 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_69f76e841b54819097e7fa768bbc70b2 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd6dbd1b648190b1a0b391c03aebc5 |
completed | May 8, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69fd6a9020548190bbfa845360ac85fb |
completed | May 8, 2026, 4:46 a.m. |
Created at: May 3, 2026, 4:13 p.m.