Triple
T118903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delphi |
E2400
|
entity |
| Predicate | modernSettlementNearby |
P3883
|
FINISHED |
| Object | modern town of Delphi |
—
|
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: modern town of Delphi | Statement: [Delphi, modernSettlementNearby, modern town of Delphi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modernSettlementNearby Context triple: [Delphi, modernSettlementNearby, modern town of Delphi]
-
A.
hasNearbyTown
chosen
Indicates that one location has a town situated close to it in geographic proximity.
-
B.
inspiredSettlement
Indicates that one entity’s ideas, actions, or example motivated or influenced the creation, development, or characteristics of a particular settlement.
-
C.
originalSettlement
Indicates that one entity is the initial or first-established settlement location associated with another entity.
-
D.
hasNearbyCommunity
Indicates that one entity has another community located close to it in geographic or spatial terms.
-
E.
hasCityStatusSettlement
Indicates that a settlement possesses official recognition or designation as a city.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25646d5088190a057989c32da3a90 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.