Triple
T34390576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Tarentum |
E882690
|
entity |
| Predicate | hasEarlierSettlement |
P40158
|
FINISHED |
| Object | Greek Taras |
—
|
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: Greek Taras | Statement: [Roman Tarentum, hasEarlierSettlement, Greek Taras]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarlierSettlement Context triple: [Roman Tarentum, hasEarlierSettlement, Greek Taras]
-
A.
hasSettlementAround
Indicates that a settlement is located in the surrounding area of a specified place or feature.
-
B.
earlierSettlement
chosen
Indicates that one settlement or agreement occurred or was reached before another in time.
-
C.
hasSubsettlement
Indicates that one settlement includes another, smaller settlement as a subordinate or component part.
-
D.
isEarlySettlementOf
Indicates that one settlement represents an earlier or initial phase, version, or establishment of another settlement.
-
E.
hasSettlementHistory
Indicates that an entity has a documented history of human settlement or habitation in relation to another entity (such as a place or time period).
- 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_69f349c0219881909393bbbc1edc8161 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.