Triple
T29545258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hittite kings |
E749612
|
entity |
| Predicate | earliestAttestedKing |
P170391
|
FINISHED |
| Object | Hattusili I |
—
|
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: Hattusili I | Statement: [Hittite kings, earliestAttestedKing, Hattusili I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestAttestedKing Context triple: [Hittite kings, earliestAttestedKing, Hattusili I]
-
A.
earliestWellAttestedKing
chosen
Indicates that the subject is recognized as the earliest historically well-documented king of the referenced polity or lineage.
-
B.
earliestKingdom
Indicates that one kingdom is the chronologically first or oldest among a specified set of kingdoms.
-
C.
firstMonarch
Indicates that the subject is the first monarch (initial ruler) of the object polity or domain.
-
D.
earliestRecordedChief
Indicates that the subject is the first (earliest in time) individual recorded as holding the position of chief for the object.
-
E.
predecessorAsKingOfMycenae
Indicates that one entity served as the immediately preceding king of Mycenae relative to 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_69f0bd48691081908cecad39bac591e0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 28, 2026, 5:06 p.m.