Triple
T32300709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heraclias |
E825229
|
entity |
| Predicate | hasWorkTitleInLatinAlphabet |
P159002
|
FINISHED |
| Object | Heraclias |
—
|
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: Heraclias | Statement: [Heraclias, hasWorkTitleInLatinAlphabet, Heraclias]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkTitleInLatinAlphabet Context triple: [Heraclias, hasWorkTitleInLatinAlphabet, Heraclias]
-
A.
hasWorkTitleInPinyin
Indicates that an entity’s work title is represented in the Pinyin (romanized Chinese) form.
-
B.
workTitleInLatinScript
chosen
Indicates that the title of a work is expressed using a Latin-based writing system.
-
C.
hasTitleWork
Indicates that an entity is associated with a specific work by its title (i.e., the entity has or bears that work’s title).
-
D.
hasLatinTitle
Indicates that an entity possesses a title or name expressed in Latin.
-
E.
hasWorkTitleType
Indicates that an entity holds a specific category or type of work-related title (e.g., job title type or role classification).
- 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_69f349115304819084ee91d345b6c8aa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd8e5f7c4c8190ab8e2f2a7bb1bd79 |
completed | May 8, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fd8d8a16f08190b9e880901bfa44fe |
completed | May 8, 2026, 7:15 a.m. |
Created at: May 1, 2026, 12:45 a.m.