Triple
T18308731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nisaba Godrej |
E438558
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Nisaba |
—
|
NE NERFINISHED |
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: Nisaba | Statement: [Nisaba Godrej, givenName, Nisaba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nisaba Context triple: [Nisaba Godrej, givenName, Nisaba]
-
A.
Rimat-Ninsun
Rimat-Ninsun is a Mesopotamian goddess, best known as the wise mother of the hero Gilgamesh in the Epic of Gilgamesh.
-
B.
Sabis
Sabis is a Turkish surname most notably borne by Ali İhsan Sabis, an Ottoman and early Republican-era military officer.
-
C.
Nabu
chosen
Nabu is the Mesopotamian god of wisdom and writing, revered as the divine scribe and patron of scribes.
-
D.
Isinai
Isinai is an Austronesian language spoken by the Isinai people of Nueva Vizcaya in the northern Philippines.
-
E.
Mundaka
Mundaka is a picturesque coastal town in the Basque Country of northern Spain, renowned for its world-class left-hand surfing wave and traditional fishing-port charm.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021709f88190a8047dd57edc2029 |
completed | April 19, 2026, 4:25 p.m. |
Created at: April 10, 2026, 10:35 a.m.