Triple
T9894160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ise-ebi spiny lobster |
E181526
|
entity |
| Predicate | hasRomanizedJapaneseName |
P2508
|
FINISHED |
| Object | Ise-ebi |
—
|
LITERAL 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: Ise-ebi | Statement: [Ise-ebi spiny lobster, hasRomanizedJapaneseName, Ise-ebi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRomanizedJapaneseName Context triple: [Ise-ebi spiny lobster, hasRomanizedJapaneseName, Ise-ebi]
-
A.
hasRomanizationOf
chosen
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
hasNameInJapanese
Indicates that an entity is associated with a specific name expressed in the Japanese language.
-
C.
hasHakkaRomanization
Indicates that an entity is associated with a specific representation of its name or term in Hakka Romanization.
-
D.
officialNameInRomaji
Indicates that an entity’s official name is written using the Roman alphabet (romaji) representation.
-
E.
usesKatakanaFor
Indicates that one entity is written or represented using katakana script in relation to another entity.
- F. None of above.
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_69ca8283a6708190801af7a25a7ebb9f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb48271d48190b718c7f6b2fe315b |
completed | April 2, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69cd1d872d50819096b7ab166a8decf1 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:39 p.m.