Triple
T13404646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | École française d’Athènes |
E319920
|
entity |
| Predicate | hasResearchStationAt |
P2881
|
FINISHED |
| Object | Delphi |
E2400
|
NE FINISHED |
How this triple was built (3 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: Delphi | Statement: [École française d’Athènes, hasResearchStationAt, Delphi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delphi Context triple: [École française d’Athènes, hasResearchStationAt, Delphi]
-
A.
Delphi
chosen
Delphi is an ancient Greek sanctuary and archaeological site famed for the Oracle of Apollo and its central role in classical Greek religion and culture.
-
B.
Delphi
Delphi is a central antagonist in the stage play "Harry Potter and the Cursed Child," portrayed as a mysterious young witch with a powerful and dangerous connection to Voldemort.
-
C.
DELPHI
DELPHI was a major particle physics detector experiment at CERN’s Large Electron–Positron Collider that studied high-energy electron–positron collisions to test the Standard Model and search for new phenomena.
-
D.
Delphi (programming language)
Delphi is an object-oriented, rapid application development programming language and environment derived from Pascal, primarily used for building native Windows applications.
-
E.
Embarcadero
Embarcadero is a historic waterfront district in San Francisco known for its piers, ferry terminal, and scenic promenade along the bay.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasResearchStationAt Context triple: [École française d’Athènes, hasResearchStationAt, Delphi]
-
A.
containsResearchStation
chosen
Indicates that one entity geographically includes or hosts a research station within its boundaries.
-
B.
maintainedResearchStation
Indicates that an entity was responsible for operating, supporting, or keeping a research station in working condition over a period of time.
-
C.
isPrimarySpaceportOf
Indicates that a given spaceport serves as the main or principal launch and operations facility for a specified region, organization, or celestial body.
-
D.
hasResearchCentersIn
Indicates that an entity maintains or operates research centers located within a specified place or region.
-
E.
wasColonyOf
Indicates that one entity functioned as a colony under the political control or administration of another entity.
- F. None of above.
Provenance (4 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_69d806b943cc8190b6af624d385d7e12 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbae4ae47081909b68a9aaa62fd4c7 |
completed | April 12, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7307904608190ad647f741c08dc42 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69d9a0355de48190bb3fb96912e20df3 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:34 p.m.