Triple
T4725635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manobo |
E104876
|
entity |
| Predicate | hasSubgroup |
P747
|
FINISHED |
| Object |
Higaonon
The Higaonon are an Indigenous Lumad group in Mindanao, Philippines, known for their upland farming, rich oral traditions, and strong customary laws tied to ancestral forest territories.
|
E463906
|
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: Higaonon | Statement: [Manobo, hasSubgroup, Higaonon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Higaonon Context triple: [Manobo, hasSubgroup, Higaonon]
-
A.
Asokoro
Asokoro is an upscale residential and administrative district in Abuja, Nigeria, known for hosting many government institutions, embassies, and high-profile residents.
-
B.
Hagonoy
Hagonoy is a coastal municipality in the province of Bulacan in the Philippines, known for its fishing industry and aquaculture.
-
C.
Miyakoan
Miyakoan is a Ryukyuan language spoken primarily on the Miyako Islands of Japan, distinct from standard Japanese and recognized as endangered.
-
D.
Kusaie
Kusaie is an alternate name for the Kosraean language spoken on the Micronesian island of Kosrae.
-
E.
Amadioha
Amadioha is a major deity in Igbo traditional religion, revered as the god of thunder, lightning, justice, and moral order.
- 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: Higaonon Triple: [Manobo, hasSubgroup, Higaonon]
Generated description
The Higaonon are an Indigenous Lumad group in Mindanao, Philippines, known for their upland farming, rich oral traditions, and strong customary laws tied to ancestral forest territories.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Higaonon Target entity description: The Higaonon are an Indigenous Lumad group in Mindanao, Philippines, known for their upland farming, rich oral traditions, and strong customary laws tied to ancestral forest territories.
-
A.
Asokoro
Asokoro is an upscale residential and administrative district in Abuja, Nigeria, known for hosting many government institutions, embassies, and high-profile residents.
-
B.
Hagonoy
Hagonoy is a coastal municipality in the province of Bulacan in the Philippines, known for its fishing industry and aquaculture.
-
C.
Miyakoan
Miyakoan is a Ryukyuan language spoken primarily on the Miyako Islands of Japan, distinct from standard Japanese and recognized as endangered.
-
D.
Kusaie
Kusaie is an alternate name for the Kosraean language spoken on the Micronesian island of Kosrae.
-
E.
Amadioha
Amadioha is a major deity in Igbo traditional religion, revered as the god of thunder, lightning, justice, and moral order.
- 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_69bd43ed84648190ae0b7ee8e8d00482 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6446b42081908e023979c9685730 |
completed | March 20, 2026, 3:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be109c67648190ba9bda7fc5cb3dd1 |
completed | March 21, 2026, 3:29 a.m. |
| NEDg | Description generation | batch_69be134fbc088190a2c7b3c3e7f00584 |
completed | March 21, 2026, 3:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be13e813e08190842ad5c2ad8e47cc |
completed | March 21, 2026, 3:43 a.m. |
Created at: March 20, 2026, 1:18 p.m.