Triple
T17288072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Te Arawa iwi |
E419709
|
entity |
| Predicate | hasAncestor |
P369
|
FINISHED |
| Object |
Hei
Hei is an important Polynesian ancestor figure recognized in Māori tradition, particularly within the whakapapa (genealogy) of the Te Arawa iwi.
|
E1260103
|
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: Hei | Statement: [Te Arawa iwi, hasAncestor, Hei]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hei Context triple: [Te Arawa iwi, hasAncestor, Hei]
-
A.
Hei
Hei is a Japanese given name element commonly used in masculine names, often conveying meanings related to peace or soldiers depending on the kanji used.
-
B.
Hein
Hein is a Dutch surname most notably borne by Piet Hein, a renowned 17th-century naval officer and folk hero of the Dutch Republic.
-
C.
Hekinan
Hekinan is a coastal industrial city in central Japan known for its manufacturing sector and location along Mikawa Bay in Aichi Prefecture.
-
D.
Heins
Heins is a variant form of the Dutch surname Heinsius, historically associated with notable scholars and statesmen in the Netherlands.
-
E.
Hieda
Hieda is a Japanese surname notably associated with historical and literary figures in classical Japanese records and folklore.
- 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: Hei Triple: [Te Arawa iwi, hasAncestor, Hei]
Generated description
Hei is an important Polynesian ancestor figure recognized in Māori tradition, particularly within the whakapapa (genealogy) of the Te Arawa iwi.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hei Target entity description: Hei is an important Polynesian ancestor figure recognized in Māori tradition, particularly within the whakapapa (genealogy) of the Te Arawa iwi.
-
A.
Hei
Hei is a Japanese given name element commonly used in masculine names, often conveying meanings related to peace or soldiers depending on the kanji used.
-
B.
Hein
Hein is a Dutch surname most notably borne by Piet Hein, a renowned 17th-century naval officer and folk hero of the Dutch Republic.
-
C.
Hekinan
Hekinan is a coastal industrial city in central Japan known for its manufacturing sector and location along Mikawa Bay in Aichi Prefecture.
-
D.
Heins
Heins is a variant form of the Dutch surname Heinsius, historically associated with notable scholars and statesmen in the Netherlands.
-
E.
Hieda
Hieda is a Japanese surname notably associated with historical and literary figures in classical Japanese records and folklore.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43780fad88190b82193c8335e2f11 |
completed | April 19, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a017957c738819087341bcd51b55114 |
completed | May 11, 2026, 6:38 a.m. |
| NEDg | Description generation | batch_6a0179f16af481909f409adb5367f021 |
completed | May 11, 2026, 6:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a017ad8480881909ca9a9982585b08d |
completed | May 11, 2026, 6:44 a.m. |
Created at: April 10, 2026, 5:40 a.m.