Triple
T33983598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moanda |
E871351
|
entity |
| Predicate | abbreviationOfMajorEmployer |
P179871
|
FINISHED |
| Object |
COMILOG
COMILOG is a major mining company, best known for its large manganese operations in and around Moanda in Gabon.
|
E2076631
|
NE FINISHED |
How this triple was built (3 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: COMILOG | Statement: [Moanda, abbreviationOfMajorEmployer, COMILOG]
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: COMILOG Triple: [Moanda, abbreviationOfMajorEmployer, COMILOG]
Generated description
COMILOG is a major mining company, best known for its large manganese operations in and around Moanda in Gabon.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: abbreviationOfMajorEmployer Context triple: [Moanda, abbreviationOfMajorEmployer, COMILOG]
-
A.
hasMajorEmployer
Indicates that an entity has a primary or most significant employer with which it is chiefly affiliated for work or occupation.
-
B.
typicalEmployer
Indicates that one entity is the kind of organization or person that commonly or usually employs the other entity.
-
C.
hasMajorEmployerType
Indicates the type or category of major employer associated with an entity.
-
D.
majorEmployerCity
Indicates that a city is a primary or significant employer of a given entity (such as an organization or population).
-
E.
typicalEmployerUnit
Indicates that one entity is the standard or characteristic organizational unit that employs or is expected to employ another entity.
- F. None of above. chosen
Provenance (7 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_69f3499e964c8190b674b03f6f791b4b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f728a345488190bd7e6751b09ac591 |
completed | May 3, 2026, 10:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3692da34508190bc1e6077f1f41305 |
completed | June 20, 2026, 1:17 p.m. |
| NEDg | Description generation | batch_6a3693820ad081909280cf562695e90f |
completed | June 20, 2026, 1:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a36941c84ac8190ab0f8f338320ceec |
completed | June 20, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69f7283ef2608190a7a85d7e7f5332c0 |
completed | May 3, 2026, 10:49 a.m. |
| PDg | Predicate description generation | batch_69f728a1a0d081909e1b4465e7b88390 |
completed | May 3, 2026, 10:51 a.m. |
Created at: May 1, 2026, 1:50 a.m.