Triple
T8968314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sama-Bajau peoples |
E214194
|
entity |
| Predicate | subgroup |
P10
|
FINISHED |
| Object |
Sama Dea
Sama Dea are a subgroup of the Sama-Bajau maritime peoples of Southeast Asia, traditionally known for their seafaring lifestyle and coastal settlements.
|
E769631
|
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: Sama Dea | Statement: [Sama-Bajau peoples, subgroup, Sama Dea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sama Dea Context triple: [Sama-Bajau peoples, subgroup, Sama Dea]
-
A.
Rubiana
Rubiana is an alternative name for Roviana, a language and cultural region of the Solomon Islands in the western Pacific.
-
B.
Fairuza
Fairuza is a feminine given name most famously borne by American actress Fairuza Balk.
-
C.
D'Lila
D'Lila is one of the twin daughters of music mogul Sean "Diddy" Combs and the late model Kim Porter.
-
D.
Vita Aldhelmi
Vita Aldhelmi is a medieval Latin hagiographical biography of St Aldhelm written by the English historian and monk William of Malmesbury.
-
E.
Santha Faiia
Santha Faiia is a photographer known for her work documenting ancient sacred sites and for being married to author and researcher Graham Hancock.
- 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: Sama Dea Triple: [Sama-Bajau peoples, subgroup, Sama Dea]
Generated description
Sama Dea are a subgroup of the Sama-Bajau maritime peoples of Southeast Asia, traditionally known for their seafaring lifestyle and coastal settlements.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sama Dea Target entity description: Sama Dea are a subgroup of the Sama-Bajau maritime peoples of Southeast Asia, traditionally known for their seafaring lifestyle and coastal settlements.
-
A.
Rubiana
Rubiana is an alternative name for Roviana, a language and cultural region of the Solomon Islands in the western Pacific.
-
B.
Fairuza
Fairuza is a feminine given name most famously borne by American actress Fairuza Balk.
-
C.
D'Lila
D'Lila is one of the twin daughters of music mogul Sean "Diddy" Combs and the late model Kim Porter.
-
D.
Vita Aldhelmi
Vita Aldhelmi is a medieval Latin hagiographical biography of St Aldhelm written by the English historian and monk William of Malmesbury.
-
E.
Santha Faiia
Santha Faiia is a photographer known for her work documenting ancient sacred sites and for being married to author and researcher Graham Hancock.
- 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_69ca839dbf608190a2f5990477115d29 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6764aca48190a5e472d1b6841886 |
completed | April 1, 2026, 12:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc95cbc4c8190a3ac582f735eeb35 |
completed | April 3, 2026, 2:06 p.m. |
| NEDg | Description generation | batch_69cfca41aed08190a5107597625e4b61 |
completed | April 3, 2026, 2:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfcaba165081908c7bbfb905356942 |
completed | April 3, 2026, 2:12 p.m. |
Created at: March 30, 2026, 7:01 p.m.