Triple
T44125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greece |
E865
|
entity |
| Predicate | UNESCOWorldHeritageSite |
P923
|
FINISHED |
| Object |
Delphi
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.
|
E2400
|
NE FINISHED |
How this triple was built (4 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: [Greece, UNESCOWorldHeritageSite, Delphi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delphi Context triple: [Greece, UNESCOWorldHeritageSite, Delphi]
-
A.
Pascal
Pascal is a high-level, strongly typed procedural programming language designed by Niklaus Wirth in the late 1960s, widely used for teaching structured programming and data structuring concepts.
-
B.
Veritas
Veritas is the Latin word for "truth" and is famously used as the motto of Harvard University.
-
C.
Theodor
Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
-
D.
Gori
Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
-
E.
Vichy
Vichy is a spa town in central France renowned for its thermal springs, health resorts, and role as the seat of the World War II Vichy regime.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Delphi Triple: [Greece, UNESCOWorldHeritageSite, Delphi]
Generated description
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.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Delphi Target entity description: 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.
-
A.
Pascal
Pascal is a high-level, strongly typed procedural programming language designed by Niklaus Wirth in the late 1960s, widely used for teaching structured programming and data structuring concepts.
-
B.
Veritas
Veritas is the Latin word for "truth" and is famously used as the motto of Harvard University.
-
C.
Theodor
Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
-
D.
Gori
Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
-
E.
Vichy
Vichy is a spa town in central France renowned for its thermal springs, health resorts, and role as the seat of the World War II Vichy regime.
- F. None of above. chosen
Provenance (5 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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24ae36824819080e8336a3c9f9bf8 |
completed | Feb. 28, 2026, 1:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a24e63a9848190a0f38b23521804e6 |
completed | Feb. 28, 2026, 2:09 a.m. |
| NEDg | Description generation | batch_69a24efe21148190849accf51a2632f0 |
completed | Feb. 28, 2026, 2:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a24fcbeee4819087186dada7466dfe |
completed | Feb. 28, 2026, 2:15 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.