Triple
T15959561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. John Carter |
E387021
|
entity |
| Predicate | romanticRelationship |
P9994
|
FINISHED |
| Object |
Kem Likasu
Kem Likasu is a Congolese refugee and medical student who becomes a close colleague and love interest of Dr. John Carter on the television series "ER."
|
E1186219
|
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: Kem Likasu | Statement: [Dr. John Carter, romanticRelationship, Kem Likasu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kem Likasu Context triple: [Dr. John Carter, romanticRelationship, Kem Likasu]
-
A.
Kem
Kem is a historic town and seaport in northern Russia on the White Sea, long associated with Pomor seafaring and trade.
-
B.
Kiesen
Kiesen is a municipality in the canton of Bern, Switzerland, served by a station on the Bern–Thun railway line.
-
C.
Kemuel
Kemuel is a minor biblical figure mentioned in the Hebrew Bible as one of the descendants in Abraham’s extended family line.
-
D.
Kao
Kao is a Chinese surname borne by numerous individuals, including notable figures in science, business, and the arts.
-
E.
Kao
Kao is a volcanic island in the Haʻapai group of Tonga, notable for being one of the country's highest and most prominent volcanic peaks.
- 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: Kem Likasu Triple: [Dr. John Carter, romanticRelationship, Kem Likasu]
Generated description
Kem Likasu is a Congolese refugee and medical student who becomes a close colleague and love interest of Dr. John Carter on the television series "ER."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kem Likasu Target entity description: Kem Likasu is a Congolese refugee and medical student who becomes a close colleague and love interest of Dr. John Carter on the television series "ER."
-
A.
Kem
Kem is a historic town and seaport in northern Russia on the White Sea, long associated with Pomor seafaring and trade.
-
B.
Kiesen
Kiesen is a municipality in the canton of Bern, Switzerland, served by a station on the Bern–Thun railway line.
-
C.
Kemuel
Kemuel is a minor biblical figure mentioned in the Hebrew Bible as one of the descendants in Abraham’s extended family line.
-
D.
Kao
Kao is a Chinese surname borne by numerous individuals, including notable figures in science, business, and the arts.
-
E.
Kao
Kao is a volcanic island in the Haʻapai group of Tonga, notable for being one of the country's highest and most prominent volcanic peaks.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156fe82d081908b5d41bc5a709de2 |
completed | April 16, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe806ef4819095a4dfe104d0bdc8 |
completed | May 9, 2026, 11:08 p.m. |
| NEDg | Description generation | batch_69ffbf61b2ec81909c0f32613bb91a82 |
completed | May 9, 2026, 11:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffbfddd0348190baab794f613c71bf |
completed | May 9, 2026, 11:14 p.m. |
Created at: April 10, 2026, 4:53 a.m.