Triple
T9529079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cap Go Meh |
E229839
|
entity |
| Predicate | featuresRitual |
P25858
|
FINISHED |
| Object |
Tatung
Tatung are spirit-medium performers in Indonesian Chinese culture, especially prominent during Cap Go Meh celebrations, who enter trance states to carry out acts of ritual protection and blessing.
|
E806036
|
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: Tatung | Statement: [Cap Go Meh, featuresRitual, Tatung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tatung Context triple: [Cap Go Meh, featuresRitual, Tatung]
-
A.
Tsien
Tsien is a Chinese surname borne by several notable figures in science and engineering, including biophysicist Richard Tsien.
-
B.
Tawailia
Tawailia is an alternate name for the Uma language, an Austronesian language spoken in parts of Indonesia.
-
C.
Hengchi
Hengchi is an electric vehicle brand developed by the Chinese conglomerate Evergrande Group as part of its push into the new energy automotive industry.
-
D.
Shandao
Shandao was a prominent 7th-century Chinese Buddhist monk and commentator whose writings systematized and greatly influenced the development of Pure Land Buddhism.
-
E.
Mibuchi
Mibuchi is a Japanese surname borne by individuals such as Tadahiko Mibuchi.
- 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: Tatung Triple: [Cap Go Meh, featuresRitual, Tatung]
Generated description
Tatung are spirit-medium performers in Indonesian Chinese culture, especially prominent during Cap Go Meh celebrations, who enter trance states to carry out acts of ritual protection and blessing.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tatung Target entity description: Tatung are spirit-medium performers in Indonesian Chinese culture, especially prominent during Cap Go Meh celebrations, who enter trance states to carry out acts of ritual protection and blessing.
-
A.
Tsien
Tsien is a Chinese surname borne by several notable figures in science and engineering, including biophysicist Richard Tsien.
-
B.
Tawailia
Tawailia is an alternate name for the Uma language, an Austronesian language spoken in parts of Indonesia.
-
C.
Hengchi
Hengchi is an electric vehicle brand developed by the Chinese conglomerate Evergrande Group as part of its push into the new energy automotive industry.
-
D.
Shandao
Shandao was a prominent 7th-century Chinese Buddhist monk and commentator whose writings systematized and greatly influenced the development of Pure Land Buddhism.
-
E.
Mibuchi
Mibuchi is a Japanese surname borne by individuals such as Tadahiko Mibuchi.
- 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_69ca8479934c81908006d0e6e970ae05 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98b1b93481909812245ac14e4988 |
completed | April 1, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c30c6008190b2eff99d74f18070 |
completed | April 4, 2026, 5:36 p.m. |
| NEDg | Description generation | batch_69d14ea0ae408190bcb375a2540c3221 |
completed | April 4, 2026, 5:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d14f13fcdc8190a227d756f1342f16 |
completed | April 4, 2026, 5:49 p.m. |
Created at: March 30, 2026, 8 p.m.