Triple
T7579213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German Turfan expeditions |
E179441
|
entity |
| Predicate | significantPlace |
P1098
|
FINISHED |
| Object |
Sängim
Sängim is an archaeological site in the Turfan region of Xinjiang, China, known for yielding important Central Asian and Silk Road-era artifacts studied by the German Turfan expeditions.
|
E675039
|
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: Sängim | Statement: [German Turfan expeditions, significantPlace, Sängim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sängim Context triple: [German Turfan expeditions, significantPlace, Sängim]
-
A.
Syvota
Syvota is a coastal village and popular tourist resort on the Ionian Sea in northwestern Greece, known for its scenic bays and nearby islands.
-
B.
Söphchen
Söphchen is a German affectionate diminutive form of the given name Sophie.
-
C.
Skeheenarinky
Skeheenarinky is a small rural village in southern Ireland known for its scenic countryside and traditional community character.
-
D.
Seille
Seille is a river in eastern France that flows through the regions of Jura and Saône-et-Loire before joining the Saône.
-
E.
Sõru
Sõru is a small port village on the southern coast of Hiiumaa Island in Estonia, known for its ferry connection to the mainland and maritime setting.
- 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: Sängim Triple: [German Turfan expeditions, significantPlace, Sängim]
Generated description
Sängim is an archaeological site in the Turfan region of Xinjiang, China, known for yielding important Central Asian and Silk Road-era artifacts studied by the German Turfan expeditions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sängim Target entity description: Sängim is an archaeological site in the Turfan region of Xinjiang, China, known for yielding important Central Asian and Silk Road-era artifacts studied by the German Turfan expeditions.
-
A.
Syvota
Syvota is a coastal village and popular tourist resort on the Ionian Sea in northwestern Greece, known for its scenic bays and nearby islands.
-
B.
Söphchen
Söphchen is a German affectionate diminutive form of the given name Sophie.
-
C.
Skeheenarinky
Skeheenarinky is a small rural village in southern Ireland known for its scenic countryside and traditional community character.
-
D.
Seille
Seille is a river in eastern France that flows through the regions of Jura and Saône-et-Loire before joining the Saône.
-
E.
Sõru
Sõru is a small port village on the southern coast of Hiiumaa Island in Estonia, known for its ferry connection to the mainland and maritime setting.
- 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_69c69f327db881909a21ae3b156f8ded |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f97460a481909d61fba555567b66 |
completed | March 27, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8616d87f881909fe23220dc77167c |
completed | March 28, 2026, 11:17 p.m. |
| NEDg | Description generation | batch_69c8625282bc8190bd1eecc13c1d4744 |
completed | March 28, 2026, 11:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8630fe8608190afc7b67d9a80240b |
completed | March 28, 2026, 11:24 p.m. |
Created at: March 27, 2026, 3:52 p.m.