Triple
T11507118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ultar Sar |
E272812
|
entity |
| Predicate | firstAscentBy |
P1321
|
FINISHED |
| Object |
Akito Yamazaki
Akito Yamazaki is a mountaineer known for making the first recorded ascent of the Karakoram peak Ultar Sar.
|
E1290258
|
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: Akito Yamazaki | Statement: [Ultar Sar, firstAscentBy, Akito Yamazaki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akito Yamazaki Context triple: [Ultar Sar, firstAscentBy, Akito Yamazaki]
-
A.
Makoto Yamashita
Makoto Yamashita is a Japanese politician serving as the governor of Nara Prefecture.
-
B.
Masayuki Hyodo
Masayuki Hyodo is a Japanese business executive best known for serving as president and CEO of the major trading company Sumitomo Corporation.
-
C.
Shinichi Tamura
Shinichi Tamura is a key executive and scientific leader associated with Heptares Therapeutics, a biopharmaceutical company specializing in G protein-coupled receptor (GPCR) drug discovery.
-
D.
Makoto Uchida
Makoto Uchida is a Japanese automotive executive who serves as the chief executive officer of Nissan Motor Co.
-
E.
Tetsu Katayama
Tetsu Katayama was a Japanese socialist politician who served as Japan’s first postwar prime minister and the first from a socialist party.
- 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: Akito Yamazaki Triple: [Ultar Sar, firstAscentBy, Akito Yamazaki]
Generated description
Akito Yamazaki is a mountaineer known for making the first recorded ascent of the Karakoram peak Ultar Sar.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Akito Yamazaki Target entity description: Akito Yamazaki is a mountaineer known for making the first recorded ascent of the Karakoram peak Ultar Sar.
-
A.
Makoto Yamashita
Makoto Yamashita is a Japanese politician serving as the governor of Nara Prefecture.
-
B.
Masayuki Hyodo
Masayuki Hyodo is a Japanese business executive best known for serving as president and CEO of the major trading company Sumitomo Corporation.
-
C.
Shinichi Tamura
Shinichi Tamura is a key executive and scientific leader associated with Heptares Therapeutics, a biopharmaceutical company specializing in G protein-coupled receptor (GPCR) drug discovery.
-
D.
Makoto Uchida
Makoto Uchida is a Japanese automotive executive who serves as the chief executive officer of Nissan Motor Co.
-
E.
Tetsu Katayama
Tetsu Katayama was a Japanese socialist politician who served as Japan’s first postwar prime minister and the first from a socialist party.
- 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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d86db43a648190be859bec2fe9f43b |
completed | April 10, 2026, 3:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0306dc4d1481908bce52d757effc59 |
completed | May 12, 2026, 10:54 a.m. |
| NEDg | Description generation | batch_6a03075d0df4819093e20f299f0824a8 |
completed | May 12, 2026, 10:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0307c1a95881909547178762490619 |
completed | May 12, 2026, 10:58 a.m. |
Created at: April 8, 2026, 9:36 p.m.