Triple
T16201600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Papingo |
E393213
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Astraka Towers |
E1199612
|
NE 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: Astraka Towers | Statement: [Papingo, near, Astraka Towers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Astraka Towers Context triple: [Papingo, near, Astraka Towers]
-
A.
Astraka Towers
chosen
Astraka Towers is a striking series of steep limestone peaks in the Pindus Mountains of northwestern Greece, popular with hikers and climbers for its dramatic cliffs and alpine scenery.
-
B.
Broel Towers
Broel Towers are a pair of medieval defensive towers and an iconic historical symbol of the Belgian city of Kortrijk (Courtrai).
-
C.
Octan Tower
Octan Tower is the central skyscraper base of operations for the fictional fuel and energy conglomerate Octan in The LEGO Movie universe.
-
D.
Granovitaya Tower
Granovitaya Tower is a historic defensive tower that forms part of the medieval Kolomna Kremlin fortress in Russia.
-
E.
Nina Tower
Nina Tower is a prominent skyscraper complex in Tsuen Wan, Hong Kong, known for its distinctive twin-tower design and mixed-use commercial and hotel facilities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2270aa7f08190ab37aa9ff46816fc |
completed | April 17, 2026, 12:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00078db04081909f7e14b09687ba67 |
completed | May 10, 2026, 4:20 a.m. |
Created at: April 10, 2026, 5:03 a.m.